© 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. 8770
    Prev
    Next
    INDEX
    Explanations

    names and references to various media content, such as movies, actors, and specific events

    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
    314
    +0.10
    0.5%
    627
    +0.10
    0.5%
    405
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.10
    0.04
    659
    +0.10
    0.05
    314
    +0.10
    0.01
    Negative Logits
     guiName
    -0.93
    ":[{"
    -0.66
    iencies
    -0.65
    alties
    -0.63
     ."
    -0.63
     ,"
    -0.63
     '.
    -0.63
     [/
    -0.61
    âĶĢâĶĢâĶĢâĶĢ
    -0.61
    cknowled
    -0.61
    POSITIVE LOGITS
    +)
    1.44
    )
    1.43
    )/
    1.36
    ),
    1.34
    -)
    1.31
    ),"
    1.30
    )'
    1.29
    )."
    1.26
    )"
    1.26
    )]
    1.24
    Activations Density 0.139%

    No Known Activations