© 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. 12927
    Prev
    Next
    INDEX
    Explanations

    references to proper names and credits in text, such as names of people or organizations

    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
    679
    +0.20
    0.7%
    585
    +0.15
    0.5%
    541
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    559
    +0.20
    0.03
    609
    +0.15
    0.03
    586
    +0.14
    0.03
    Negative Logits
    oshenko
    -1.19
    thin
    -1.01
    oiler
    -0.99
     retard
    -0.96
    tein
    -0.91
     deaf
    -0.90
    pton
    -0.90
    powers
    -0.89
     pretext
    -0.89
     illiter
    -0.89
    POSITIVE LOGITS
    eous
    1.27
    edIn
    1.22
     Images
    1.17
    heses
    1.10
     Photo
    1.06
     Provided
    1.04
    Phot
    1.01
     Photos
    1.01
    patrick
    0.98
    esville
    0.97
    Activations Density 0.311%

    No Known Activations