© 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. 11244
    Prev
    Next
    INDEX
    Explanations

    links to external content

    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
    50
    +0.15
    0.5%
    742
    +0.12
    0.4%
    128
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    637
    +0.15
    0.04
    128
    +0.12
    0.03
    545
    +0.11
    0.03
    Negative Logits
     "$:/
    -1.10
    esm
    -1.00
     paed
    -1.00
     CTR
    -0.93
     MFT
    -0.91
     Galile
    -0.88
    Ô
    -0.85
     subsequ
    -0.85
     Metatron
    -0.83
    issance
    -0.83
    POSITIVE LOGITS
    =
    1.11
    Trade
    1.04
    hs
    1.01
    =-
    0.93
    _(
    0.92
    work
    0.92
    ancy
    0.89
    ref
    0.89
    &
    0.87
    _{
    0.87
    Activations Density 0.350%

    No Known Activations