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

    Neuronpedia

    Jacobian LensNEW
    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. 18178
    Prev
    Next
    INDEX
    Explanations

    words related to inspiration or being inspired

    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
    314
    +0.14
    0.6%
    674
    +0.09
    0.4%
    609
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.04
    746
    +0.09
    0.03
    214
    +0.09
    0.03
    Negative Logits
     shroud
    -0.82
     hol
    -0.76
     polyg
    -0.74
     wool
    -0.73
     thereof
    -0.71
     thereto
    -0.71
     blah
    -0.69
     sanctuary
    -0.68
     orally
    -0.67
     AMERICA
    -0.66
    POSITIVE LOGITS
    ications
    1.13
    inct
    1.09
    iction
    1.09
    ased
    1.08
    initions
    1.07
    itionally
    1.07
    iliated
    1.05
    acia
    1.04
    ifully
    1.03
    osing
    1.03
    Activations Density 0.118%

    No Known Activations