© 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. 11993
    Prev
    Next
    INDEX
    Explanations

    references to questions, comments and answers in a discussion or conversation

    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
    219
    +0.08
    0.5%
    69
    +0.07
    0.4%
    377
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.08
    0.03
    176
    +0.07
    0.02
    6
    +0.07
    0.03
    Negative Logits
    anon
    -0.53
    igi
    -0.50
    OOK
    -0.48
    advertisement
    -0.47
    window
    -0.46
    itar
    -0.46
    âĹ¼
    -0.44
     Notting
    -0.43
     bay
    -0.42
     thats
    -0.41
    POSITIVE LOGITS
    DragonMagazine
    0.61
    icter
    0.48
     transc
    0.48
    halla
    0.45
    hound
    0.43
    wolf
    0.43
    fur
    0.42
    staking
    0.42
    gard
    0.42
    osponsors
    0.42
    Activations Density 0.122%

    No Known Activations