© 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. 12064
    Prev
    Next
    INDEX
    Explanations

    information related to research funding and author contributions in scientific articles

    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
    620
    +0.07
    0.5%
    268
    +0.06
    0.5%
    484
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.07
    0.02
    247
    +0.06
    0.01
    225
    +0.06
    0.01
    Negative Logits
     Random
    -0.43
     Balanced
    -0.42
     EPS
    -0.41
     Firefox
    -0.39
     Freak
    -0.38
     Leviathan
    -0.38
     Blizz
    -0.38
     Cinema
    -0.38
     Infinite
    -0.38
     Hollande
    -0.38
    POSITIVE LOGITS
    uments
    0.53
    imet
    0.49
    usted
    0.48
    dating
    0.47
    rats
    0.47
    tones
    0.46
    natureconservancy
    0.46
    sers
    0.44
    ummies
    0.44
    onyms
    0.44
    Activations Density 0.029%

    No Known Activations