© 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. 37241
    Prev
    Next
    INDEX
    Explanations

    the name "Chris" in various contexts throughout the text

    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
    236
    +0.10
    0.4%
    619
    +0.10
    0.4%
    54
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.10
    0.02
    543
    +0.10
    0.02
    519
    +0.10
    0.02
    Negative Logits
    pmwiki
    -0.78
     reconciliation
    -0.73
     rul
    -0.67
    bably
    -0.67
     lockout
    -0.66
    EMBER
    -0.65
     âĶľâĶĢâĶĢ
    -0.65
    fits
    -0.64
     archaic
    -0.64
    ursed
    -0.63
    POSITIVE LOGITS
    opher
    0.95
     Klu
    0.93
     Jericho
    0.91
     Bosh
    0.88
     Christie
    0.86
    jen
    0.85
     Isa
    0.84
     Evans
    0.84
     Nolan
    0.81
     Columbus
    0.80
    Activations Density 0.008%

    No Known Activations