© 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. 34778
    Prev
    Next
    INDEX
    Explanations

    baseball-related terms and actions involving baseball players and games

    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
    +0.18
    0.8%
    575
    +0.15
    0.6%
    261
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.18
    0.14
    288
    +0.15
    0.27
    585
    +0.11
    0.12
    Negative Logits
    ë
    -0.95
     Imperium
    -0.90
    î
    -0.85
     Beir
    -0.79
    abus
    -0.78
    AFTA
    -0.74
    agne
    -0.73
    ħĭ
    -0.72
    uters
    -0.72
    ão
    -0.71
    POSITIVE LOGITS
     pitchers
    1.15
     pitcher
    1.14
    BIP
    1.10
     batted
    1.08
     pitching
    1.06
     hitters
    1.05
     reliever
    1.05
     clubhouse
    1.04
     hitter
    1.04
     Baseball
    1.03
    Activations Density 17.284%

    No Known Activations