© 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 12288
    9. 8-RES_FS12288-JB
    11. 9852
    Prev
    Next
    INDEX
    Explanations

    passages discussing geographical regions and political or social issues related to community and society

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    728
    +0.11
    0.5%
    473
    +0.10
    0.5%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.11
    0.06
    393
    +0.10
    0.07
    363
    +0.10
    0.06
    Negative Logits
    $.
    -0.74
    +.
    -0.72
    jah
    -0.71
    ];
    -0.69
    ].
    -0.69
    .[
    -0.66
    >.
    -0.66
    requires
    -0.65
    `.
    -0.65
    "],
    -0.65
    POSITIVE LOGITS
     subsequent
    0.94
     consequently
    0.87
    rogens
    0.87
     others
    0.87
    rogen
    0.85
     associated
    0.85
     consequ
    0.84
     other
    0.83
     resultant
    0.83
     therefore
    0.81
    Activations Density 0.413%

    No Known Activations