© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32952
    Prev
    Next
    INDEX
    Explanations

    information related to sports, including player injuries, team strategies, trade possibilities, and player signings

    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
    +0.23
    0.9%
    481
    +0.14
    0.6%
    202
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.23
    0.40
    283
    +0.14
    -0.01
    86
    +0.13
    0.06
    Negative Logits
     Feminist
    -1.02
     UNESCO
    -0.90
    rika
    -0.86
     feminist
    -0.84
    aum
    -0.82
     behavi
    -0.81
     Reporting
    -0.79
     Gloria
    -0.78
     SHAR
    -0.78
     liter
    -0.77
    POSITIVE LOGITS
     undrafted
    1.34
     waivers
    1.33
     offseason
    1.22
     signings
    1.20
     rosters
    1.13
     roster
    1.12
     signing
    1.05
     salary
    1.04
    Contract
    1.03
    Draft
    1.02
    Activations Density 27.647%

    No Known Activations