© 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. 1342
    Prev
    Next
    INDEX
    Explanations

    phrases related to defending or raising awareness for a cause

    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
    206
    +0.11
    0.5%
    282
    +0.10
    0.4%
    225
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.11
    0.05
    282
    +0.10
    0.05
    510
    +0.10
    0.04
    Negative Logits
     Manufacturer
    -0.70
    interstitial
    -0.67
    asking
    -0.62
    availability
    -0.62
    UNCH
    -0.60
     Pair
    -0.59
    gradation
    -0.58
    iven
    -0.57
    roxy
    -0.57
    hy
    -0.57
    POSITIVE LOGITS
     themselves
    0.95
     contrace
    0.77
    selves
    0.74
     otherwise
    0.69
    meric
    0.69
     yourselves
    0.67
    ebook
    0.66
    pires
    0.66
     passionately
    0.65
     faiths
    0.63
    Activations Density 0.427%

    No Known Activations