Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 554
    Prev
    Next
    INDEX
    Explanations

    sports statistics and related information

    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
    160
    +0.13
    0.5%
    216
    +0.11
    0.4%
    267
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    0.01
    606
    +0.11
    0.04
    291
    +0.11
    0.04
    Negative Logits
    uras
    -0.92
    uga
    -0.85
    ute
    -0.85
    kson
    -0.84
    urated
    -0.81
    ildo
    -0.81
    cles
    -0.80
    itor
    -0.79
    adian
    -0.78
    uristic
    -0.78
    POSITIVE LOGITS
    odder
    0.90
    WN
    0.90
    aturday
    0.89
    news
    0.86
    IK
    0.84
    restling
    0.84
    YOU
    0.84
    sports
    0.82
    SPEC
    0.81
    DEF
    0.81
    Activations Density 0.306%

    No Known Activations