© 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. 23898
    Prev
    Next
    INDEX
    Explanations

    structured details regarding events and their associated information

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.14
    0.7%
    314
    +0.13
    0.6%
    727
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    727
    +0.14
    0.03
    176
    +0.13
    0.02
    609
    +0.11
    0.03
    Negative Logits
    kef
    -0.69
     .)
    -0.69
     Haram
    -0.69
     ).
    -0.65
     circumcised
    -0.63
     disg
    -0.61
     )]
    -0.59
     Antar
    -0.57
    intendo
    -0.56
     ].
    -0.56
    POSITIVE LOGITS
    %:
    1.33
    :
    1.09
    iculty
    0.87
    ':
    0.85
    :"
    0.82
    :#
    0.81
    ":{"
    0.79
    :'
    0.78
    ":
    0.77
    .:
    0.77
    Activations Density 0.135%

    No Known Activations