© 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. 37303
    Prev
    Next
    INDEX
    Explanations

    instances of the character "ľ" in 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
    480
    +0.14
    0.6%
    314
    +0.14
    0.6%
    87
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.14
    0.05
    333
    +0.14
    0.04
    168
    +0.12
    0.05
    Negative Logits
     disadvant
    -0.80
     womb
    -0.76
     condem
    -0.75
     conduc
    -0.74
     manif
    -0.74
     slic
    -0.73
     altern
    -0.73
     apes
    -0.73
     mounts
    -0.72
     limb
    -0.72
    POSITIVE LOGITS
    ï¸ı
    1.19
    âĶĢâĶĢ
    0.93
    à¼
    0.92
    \/\/
    0.86
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.85
     Edited
    0.83
    ×Ķ
    0.83
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.81
    ishable
    0.79
    ihad
    0.79
    Activations Density 0.088%

    No Known Activations