© 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 EvalsExportsinterp-engineNEWAPI 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. 8273
    Prev
    Next
    INDEX
    Explanations

    references to fantasy role-playing games, especially actions related to defeating enemies, gaining skills, and acquiring items

    oai_token-act-pair · gpt-3.5-turbo
    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
    47
    +0.04
    0.5%
    721
    +0.04
    0.5%
    716
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.04
    0.01
    369
    +0.04
    0.00
    122
    +0.04
    0.00
    Negative Logits
     Paste
    -0.29
     Vlad
    -0.25
     Wald
    -0.24
    Translation
    -0.24
    éĹĺ
    -0.23
     Vox
    -0.23
    essler
    -0.23
     Milo
    -0.23
     smartest
    -0.23
     Gutierrez
    -0.23
    POSITIVE LOGITS
    iren
    0.31
    ppard
    0.28
    tackle
    0.28
    linger
    0.25
    aspx
    0.25
    ratulations
    0.25
    ciples
    0.25
    pora
    0.24
    ree
    0.24
     congr
    0.24
    Activations Density 0.002%

    No Known Activations