© 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. 7945
    Prev
    Next
    INDEX
    Explanations

    words related to actions or initiatives being taken

    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
    33
    +0.15
    0.5%
    642
    +0.13
    0.4%
    587
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.15
    0.03
    587
    +0.13
    0.04
    717
    +0.13
    0.03
    Negative Logits
     underrated
    -0.93
    lia
    -0.85
    ili
    -0.85
    activate
    -0.85
    iol
    -0.83
    ugg
    -0.82
    outer
    -0.81
     neighb
    -0.81
    umbo
    -0.81
     [+
    -0.81
    POSITIVE LOGITS
    mberg
    1.30
    posts
    1.22
    plain
    1.17
     outlines
    1.13
    \\\\\\\\
    1.07
    RFC
    1.05
     Goals
    1.05
    bold
    1.04
     outlining
    1.03
    sonian
    0.99
    Activations Density 0.475%

    No Known Activations