© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18773
    Prev
    Next
    INDEX
    Explanations

    keywords related to political and social issues, as well as technical terms and concepts in a diverse range of contexts

    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
    87
    +0.30
    1.6%
    669
    +0.09
    0.5%
    464
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.30
    0.06
    537
    +0.09
    0.06
    130
    +0.08
    0.04
    Negative Logits
     .)
    -0.63
     Canaver
    -0.56
    .):
    -0.55
     awoken
    -0.52
    ccording
    -0.50
     Caption
    -0.50
     Totally
    -0.50
    _-
    -0.49
    ():
    -0.48
    -+-+
    -0.48
    POSITIVE LOGITS
     etc
    0.89
     and
    0.54
    !,
    0.53
    ,
    0.53
    *,
    0.51
    +,
    0.50
     thereof
    0.48
    (),
    0.48
    ?,
    0.47
     pickup
    0.47
    Activations Density 0.573%

    No Known Activations