© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41737
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations, particularly cities and states

    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
    548
    +0.10
    0.4%
    302
    +0.09
    0.4%
    282
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.10
    0.03
    752
    +0.09
    0.03
    302
    +0.09
    0.02
    Negative Logits
    avorite
    -0.79
    hire
    -0.75
    stellar
    -0.70
    lly
    -0.70
    uddenly
    -0.69
    merce
    -0.68
     enroll
    -0.68
    gone
    -0.67
     causation
    -0.66
    NetMessage
    -0.66
    POSITIVE LOGITS
     Observer
    1.05
     Encyclopedia
    0.86
     Gazette
    0.85
     Reporter
    0.85
     Blog
    0.84
     Tribune
    0.84
    Journal
    0.83
     Journal
    0.83
     Correspond
    0.82
     Times
    0.79
    Activations Density 0.037%

    No Known Activations