© 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 1536
    9. 8-RES_FS1536-JB
    11. 1023
    Prev
    Next
    INDEX
    Explanations

    words related to political and social issues, activism, and societal challenges

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    480
    +0.54
    3.2%
    447
    +0.25
    1.5%
    266
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.54
    -0.01
    266
    +0.25
    0.28
    351
    +0.10
    0.08
    Negative Logits
    etheless
    -0.71
    also
    -0.53
     Canaver
    -0.52
    yssey
    -0.50
     GOODMAN
    -0.50
    evidence
    -0.48
    shapeshifter
    -0.46
    IBLE
    -0.46
    blance
    -0.46
    zik
    -0.46
    POSITIVE LOGITS
     etc
    0.73
     or
    0.55
    ®,
    0.49
     blah
    0.48
     versus
    0.48
    )</
    0.47
    )/
    0.44
     swe
    0.44
    !),
    0.44
     baths
    0.44
    Activations Density 11.256%

    No Known Activations