© 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. 8030
    Prev
    Next
    INDEX
    Explanations

    terms related to baseball positions and achievements

    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
    200
    +0.12
    0.5%
    760
    +0.10
    0.5%
    203
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.03
    398
    +0.10
    0.03
    708
    +0.10
    0.03
    Negative Logits
    ologically
    -0.69
    xual
    -0.69
    hran
    -0.63
    akeru
    -0.61
    osexual
    -0.60
    tty
    -0.59
    ilyn
    -0.59
    yll
    -0.58
    schild
    -0.58
    uffy
    -0.58
    POSITIVE LOGITS
    ioxide
    0.98
     Sachs
    0.97
    tein
    0.75
    midt
    0.73
    Unix
    0.72
     Ferry
    0.71
    tes
    0.66
    Spect
    0.63
    agos
    0.63
     Haku
    0.61
    Activations Density 0.195%

    No Known Activations