© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1812
    Prev
    Next
    INDEX
    Explanations

    links to specific websites and possibly some specific technical terms

    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
    639
    +0.07
    0.5%
    689
    +0.06
    0.5%
    486
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.07
    0.01
    373
    +0.06
    -0.01
    103
    +0.06
    0.01
    Negative Logits
    ivism
    -0.44
     Mex
    -0.40
    uria
    -0.40
    iii
    -0.38
     Palest
    -0.38
     Mush
    -0.38
    ©¶æ¥µ
    -0.38
    dogs
    -0.37
     Hess
    -0.37
     Ness
    -0.36
    POSITIVE LOGITS
    pmwiki
    0.48
    soType
    0.46
    FTWARE
    0.42
    Reilly
    0.41
    enegger
    0.41
    ospons
    0.39
    dayName
    0.39
    Sit
    0.38
    hler
    0.38
    ahime
    0.37
    Activations Density 0.030%

    No Known Activations