© 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 12288
    5. 8-RES_FS12288-JB
    6. 10483
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms like "Panetta"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    526
    +0.13
    0.6%
    282
    +0.12
    0.5%
    377
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.13
    0.02
    31
    +0.12
    0.02
    282
    +0.11
    0.02
    Negative Logits
     guiIcon
    -0.63
    IELD
    -0.63
     minded
    -0.62
     Yankee
    -0.61
     Gilmore
    -0.61
    ````
    -0.61
    itability
    -0.60
    INGTON
    -0.59
    enance
    -0.59
     Sheffield
    -0.58
    POSITIVE LOGITS
    orama
    1.26
    acea
    1.16
    tera
    1.10
    handle
    1.00
    handler
    0.99
    ahon
    0.99
    zers
    0.98
    alyst
    0.98
    omaly
    0.97
    icking
    0.96
    Activations Density 0.060%

    No Known Activations