© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12931
    Prev
    Next
    INDEX
    Explanations

    references to award-winning achievements or individuals

    oai_token-act-pair · gpt-3.5-turbo

    words related to awards, specifically focusing on forms of the word "winning."

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    339
    +0.20
    0.6%
    288
    +0.17
    0.5%
    731
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.20
    0.05
    174
    +0.17
    0.04
    288
    +0.14
    0.06
    Negative Logits
    alle
    -1.17
    vere
    -1.13
    onomic
    -1.11
    umm
    -1.10
    atum
    -1.08
    agen
    -1.07
    enhagen
    -1.07
    tera
    -1.05
    utation
    -1.05
    ensor
    -1.03
    POSITIVE LOGITS
     streak
    1.28
     heroine
    1.12
    NESS
    1.05
     novelist
    0.91
     headlines
    0.88
     Christine
    0.88
     Rox
    0.88
     author
    0.86
     Connor
    0.85
     Molly
    0.83
    Activations Density 0.519%

    No Known Activations