© 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. 18436
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to finance, cybersecurity, and technology

    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
    428
    +0.10
    0.5%
    391
    +0.10
    0.4%
    283
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.10
    0.04
    572
    +0.10
    0.04
    88
    +0.10
    0.03
    Negative Logits
    iets
    -0.67
    obar
    -0.64
    uterte
    -0.58
    ãĥį
    -0.58
     Citizens
    -0.57
    IDES
    -0.57
    icipated
    -0.57
     similarities
    -0.56
     Cambod
    -0.55
     Nguyen
    -0.55
    POSITIVE LOGITS
     ;)
    0.76
     ðŁĺ
    0.76
    .
    0.75
    _.
    0.73
     except
    0.72
    .�
    0.70
     :)
    0.70
    .-
    0.69
    .*
    0.68
     :-)
    0.68
    Activations Density 0.152%

    No Known Activations