© 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 24576
    9. 8-RES_FS24576-JB
    11. 9254
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles and updates on various subjects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    133
    +0.13
    0.6%
    464
    +0.12
    0.6%
    675
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.13
    0.04
    545
    +0.12
    0.02
    760
    +0.12
    0.02
    Negative Logits
    roth
    -0.94
     Palest
    -0.75
    215
    -0.74
     215
    -0.74
     Peb
    -0.72
    725
    -0.72
     Pepper
    -0.70
    ä
    -0.70
    ¡
    -0.70
     ARC
    -0.69
    POSITIVE LOGITS
    see
    0.97
     see
    0.88
     SEE
    0.83
    iz
    0.82
     Sketch
    0.82
    ix
    0.78
     analyse
    0.76
     inspect
    0.76
     picture
    0.75
    saw
    0.74
    Activations Density 0.158%

    No Known Activations