© 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. 12432
    Prev
    Next
    INDEX
    Explanations

    arguments and discussions related to public policy and social issues

    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
    720
    +0.15
    0.7%
    43
    +0.11
    0.5%
    278
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.15
    0.08
    43
    +0.11
    0.07
    546
    +0.10
    0.07
    Negative Logits
    âķIJ
    -0.73
    abouts
    -0.71
    £ı
    -0.67
     Selected
    -0.67
     Latest
    -0.67
    abo
    -0.66
    ety
    -0.66
    ãĥ¯ãĥ³
    -0.66
    ulhu
    -0.66
    »Ĵ
    -0.64
    POSITIVE LOGITS
    especially
    1.08
     thereby
    1.07
     especially
    1.04
     exacerbate
    1.02
     impair
    1.00
    particularly
    0.98
     albeit
    0.97
     worsen
    0.97
     particularly
    0.94
     exacerb
    0.94
    Activations Density 0.276%

    No Known Activations