© 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 49152
    9. 8-RES_FS49152-JB
    11. 25715
    Prev
    Next
    INDEX
    Explanations

    mentions of "bus" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    379
    +0.11
    0.5%
    484
    +0.10
    0.5%
    442
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.11
    0.01
    484
    +0.10
    0.01
    115
    +0.10
    0.01
    Negative Logits
    arily
    -0.72
    vironment
    -0.68
     Centauri
    -0.67
     marrow
    -0.65
    theless
    -0.65
    ulhu
    -0.64
    aneous
    -0.64
    AFTA
    -0.63
    anguage
    -0.61
     Doomsday
    -0.60
    POSITIVE LOGITS
    INESS
    1.25
    loads
    1.08
    hel
    1.08
    sell
    0.98
    hell
    0.97
    hes
    0.96
    ker
    0.93
    ility
    0.90
    boys
    0.88
    driver
    0.87
    Activations Density 0.006%

    No Known Activations