© 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 EvalsExportsinterp-engineNEWAPI 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. 14109
    Prev
    Next
    INDEX
    Explanations

    information about Members of Parliament (MPs) from different regions and political parties, along with their associated titles and locations

    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
    373
    +0.14
    0.6%
    602
    +0.10
    0.5%
    378
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.14
    0.03
    107
    +0.10
    0.02
    365
    +0.10
    0.01
    Negative Logits
     Mash
    -0.70
     Fa
    -0.70
     Zac
    -0.69
     Shuttle
    -0.68
     Bang
    -0.68
     Citadel
    -0.68
     Gw
    -0.67
     Tol
    -0.67
     Sik
    -0.67
     Panama
    -0.66
    POSITIVE LOGITS
    14
    0.99
    16
    0.98
    26
    0.97
    18
    0.95
    13
    0.95
    20
    0.93
    11
    0.93
    15
    0.93
    23
    0.93
    22
    0.93
    Activations Density 0.046%

    No Known Activations