© 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. 11941
    Prev
    Next
    INDEX
    Explanations

    names or terms related to significant figures or companies in the tech industry

    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
    288
    +0.12
    0.6%
    338
    +0.11
    0.5%
    739
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.12
    0.01
    145
    +0.11
    0.01
    699
    +0.11
    0.01
    Negative Logits
     sight
    -0.78
    urses
    -0.76
    uates
    -0.73
    UTERS
    -0.71
    KT
    -0.68
     lockout
    -0.66
     toxin
    -0.65
    verages
    -0.63
     diplom
    -0.62
     pity
    -0.62
    POSITIVE LOGITS
    wic
    1.32
    usky
    1.16
    oval
    1.14
    alph
    1.02
    hill
    1.01
    paper
    0.99
    boxing
    0.96
    box
    0.94
    hya
    0.93
    stone
    0.92
    Activations Density 0.013%

    No Known Activations