© 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 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. 10399
    Prev
    Next
    INDEX
    Explanations

    terms related to physical sensations and activities, such as racing, pouring, playing, streaming, and wafting

    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
    229
    +0.11
    0.5%
    262
    +0.11
    0.5%
    505
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.11
    0.05
    469
    +0.11
    0.04
    216
    +0.10
    0.04
    Negative Logits
    eka
    -0.78
    ritical
    -0.77
    zanne
    -0.76
    cision
    -0.76
    cemic
    -0.75
    ograms
    -0.73
    schild
    -0.70
    ometric
    -0.68
    ombat
    -0.67
    emale
    -0.67
    POSITIVE LOGITS
     around
    0.88
     nowhere
    0.81
     concurrently
    0.78
     underneath
    0.78
     across
    0.77
     anywhere
    0.76
     throughout
    0.76
     everywhere
    0.74
     beneath
    0.73
     towards
    0.72
    Activations Density 0.210%

    No Known Activations