© 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. 2197
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities followed by descriptions or anecdotes

    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
    393
    +0.13
    0.6%
    362
    +0.11
    0.5%
    159
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.08
    393
    +0.11
    0.05
    16
    +0.10
    0.05
    Negative Logits
    BIL
    -0.73
    Christmas
    -0.70
    ess
    -0.66
     whilst
    -0.64
    anan
    -0.63
     anew
    -0.61
     instead
    -0.61
    ILA
    -0.61
    EVA
    -0.60
    lessly
    -0.60
    POSITIVE LOGITS
     vicinity
    1.26
     periphery
    1.01
     audience
    1.01
     midst
    0.92
     profession
    0.88
     field
    0.84
     forefront
    0.83
     middle
    0.83
     area
    0.83
     same
    0.82
    Activations Density 0.209%

    No Known Activations