© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41788
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.16
    0.7%
    447
    +0.12
    0.5%
    493
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.01
    554
    +0.12
    0.01
    555
    +0.10
    0.01
    Negative Logits
    choes
    -0.88
    anus
    -0.88
    ¼
    -0.86
    hematic
    -0.81
    THER
    -0.81
    ¸
    -0.77
    YA
    -0.76
    ²¾
    -0.76
    Ń
    -0.75
    nian
    -0.74
    POSITIVE LOGITS
     endorsements
    1.10
    rities
    1.08
     endors
    1.08
     chef
    1.03
     gossip
    1.01
     chefs
    0.91
     nude
    0.84
     stunts
    0.81
     stunt
    0.81
     feud
    0.80
    Activations Density 0.020%

    No Known Activations