© 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 Local
    9. 6-RES_SCL-AJT
    11. 34035
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, specifically football and player management

    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
    393
    +0.22
    0.9%
    608
    +0.20
    0.8%
    232
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.22
    0.20
    393
    +0.20
    0.20
    362
    +0.12
    0.11
    Negative Logits
    ĸļ
    -1.03
     agre
    -0.91
    riages
    -0.81
    metics
    -0.78
    oler
    -0.76
    raid
    -0.74
    gypt
    -0.74
     condem
    -0.73
    ARDIS
    -0.71
    dayName
    -0.71
    POSITIVE LOGITS
    arching
    0.87
    manship
    0.81
    outh
    0.78
    oaded
    0.75
    things
    0.74
    legged
    0.72
    outed
    0.71
     juicy
    0.69
     highlights
    0.68
     amazing
    0.68
    Activations Density 7.179%

    No Known Activations