© 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 EvalsExportsinterp-engineNEWAPI 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. 4070
    Prev
    Next
    INDEX
    Explanations

    references to protests and demonstrations

    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
    104
    +0.12
    0.6%
    445
    +0.12
    0.5%
    336
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.12
    0.03
    445
    +0.12
    0.03
    336
    +0.11
    0.03
    Negative Logits
     nodd
    -0.80
    è¯
    -0.75
    pmwiki
    -0.75
    ãĥı
    -0.74
    ãĥ¯
    -0.74
    beam
    -0.71
    aceous
    -0.71
    Scroll
    -0.70
     Carbuncle
    -0.70
     Crusher
    -0.69
    POSITIVE LOGITS
     injust
    1.09
     injustice
    1.07
     oppression
    0.94
     closure
    0.90
     oppressive
    0.85
     eviction
    0.84
     government
    0.83
    government
    0.80
     independence
    0.80
     unjust
    0.80
    Activations Density 0.168%

    No Known Activations