© 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 Local
    9. 6-RES_SCL-AJT
    11. 31961
    Prev
    Next
    INDEX
    Explanations

    data related to sports

    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
    +0.20
    1.0%
    167
    +0.11
    0.6%
    763
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.27
    551
    +0.11
    0.14
    14
    +0.08
    0.08
    Negative Logits
     externalToEVAOnly
    -0.52
    REDACTED
    -0.52
     Publication
    -0.50
     prescribing
    -0.50
    Reply
    -0.49
     setbacks
    -0.49
    lets
    -0.48
     extremism
    -0.47
     ashes
    -0.47
     operation
    -0.47
    POSITIVE LOGITS
    ibo
    0.88
    athered
    0.80
    igh
    0.78
    asel
    0.78
    arily
    0.78
    IRD
    0.76
    blogs
    0.76
    've
    0.75
    eding
    0.74
    ighed
    0.73
    Activations Density 13.693%

    No Known Activations