© 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 3072
    5. 8-RES_FS3072-JB
    6. 686
    Prev
    Next
    INDEX
    Explanations

    updates and version numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    496
    +0.13
    0.6%
    468
    +0.11
    0.5%
    140
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.13
    0.04
    140
    +0.11
    0.04
    195
    +0.10
    0.03
    Negative Logits
    aden
    -0.83
    thing
    -0.74
    gravity
    -0.71
    zees
    -0.71
    lopp
    -0.70
    odor
    -0.69
     Fein
    -0.69
    iac
    -0.69
    ften
    -0.68
    leon
    -0.67
    POSITIVE LOGITS
     notification
    0.76
     accordingly
    0.76
     notifications
    0.75
     update
    0.73
     Notification
    0.73
    endum
    0.71
     timetable
    0.70
     updates
    0.69
     VERS
    0.68
    ments
    0.67
    Activations Density 0.538%

    No Known Activations