© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1312
    Prev
    Next
    INDEX
    Explanations

    descriptions related to sports events, particularly plays and game actions

    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
    325
    +0.19
    0.7%
    607
    +0.15
    0.5%
    160
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.19
    0.10
    531
    +0.15
    0.05
    607
    +0.14
    0.05
    Negative Logits
    ĨĴ
    -1.20
    auga
    -0.98
    ĵĺ
    -0.98
     VAT
    -0.96
     Males
    -0.95
     certific
    -0.94
     Unic
    -0.94
    «ĺ
    -0.90
    ĺħ
    -0.89
     Bore
    -0.88
    POSITIVE LOGITS
    making
    1.32
    maker
    1.21
    calling
    1.17
    offs
    1.16
    breaker
    1.15
    call
    1.14
    backs
    1.10
    makers
    1.08
    aways
    1.05
    alter
    1.03
    Activations Density 0.966%

    No Known Activations