© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7008
    Prev
    Next
    INDEX
    Explanations

    places or geographical areas

    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
    481
    +0.17
    0.8%
    642
    +0.12
    0.5%
    145
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.17
    0.03
    377
    +0.12
    0.03
    535
    +0.11
    0.02
    Negative Logits
    enstein
    -0.88
    士
    -0.76
    thood
    -0.74
    vation
    -0.72
    aldi
    -0.70
    fruit
    -0.70
    lett
    -0.70
    gement
    -0.69
    upiter
    -0.69
    inen
    -0.69
    POSITIVE LOGITS
     surrounding
    1.07
     bounded
    0.98
     vicinity
    0.96
     frequ
    0.88
     periphery
    0.87
     adjacent
    0.87
     illegally
    0.86
     bordering
    0.85
     adjoining
    0.83
     inhabited
    0.83
    Activations Density 0.064%

    No Known Activations