© 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. 35530
    Prev
    Next
    INDEX
    Explanations

    details related to sports events and activities

    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
    +0.28
    1.5%
    640
    +0.26
    1.4%
    372
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.44
    160
    +0.26
    0.28
    6
    +0.08
    0.23
    Negative Logits
     withdraw
    -0.71
     citiz
    -0.70
     prosec
    -0.68
     conclude
    -0.67
    ignt
    -0.65
     dissu
    -0.62
     overth
    -0.61
    ulkan
    -0.61
    iga
    -0.60
     neighb
    -0.59
    POSITIVE LOGITS
    Seriously
    0.82
    SHARE
    0.79
    Published
    0.78
    Sure
    0.78
    Unless
    0.78
    hello
    0.76
    Interested
    0.75
    Consider
    0.75
    Actor
    0.74
    Specifically
    0.72
    Activations Density 5.414%

    No Known Activations