© 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. 8332
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "one" used in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    393
    +0.19
    0.6%
    274
    +0.17
    0.5%
    25
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.19
    0.06
    609
    +0.17
    0.06
    366
    +0.14
    0.05
    Negative Logits
    osponsors
    -1.12
    inders
    -1.05
    avascript
    -1.00
    ucl
    -0.99
     srf
    -0.99
    iety
    -0.99
    ategory
    -0.99
    vered
    -0.99
    rench
    -0.98
    atted
    -0.97
    POSITIVE LOGITS
     Hundred
    1.27
     hundred
    1.22
    esan
    1.14
     eyed
    1.10
     sided
    1.09
    hots
    0.98
     person
    0.97
     dimensional
    0.96
     handed
    0.93
     Thousand
    0.91
    Activations Density 0.931%

    No Known Activations