© 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 Local
    9. 6-RES_SCL-AJT
    11. 33743
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.27
    2.3%
    640
    +0.23
    1.9%
    266
    +0.21
    1.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.27
    0.51
    160
    +0.23
    0.33
    6
    +0.21
    0.25
    Negative Logits
    xual
    -0.50
    aten
    -0.46
     destro
    -0.44
    ĸļ
    -0.40
    uese
    -0.39
     thous
    -0.39
    idth
    -0.39
    utical
    -0.38
    userc
    -0.38
    cffff
    -0.38
    POSITIVE LOGITS
    CVE
    0.72
    Newsletter
    0.60
    RESULTS
    0.57
    Intel
    0.54
     largeDownload
    0.53
    METHOD
    0.49
    MORE
    0.49
    Conclusion
    0.49
    Methods
    0.49
    AMY
    0.48
    Activations Density 9.609%

    No Known Activations