© 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 12288
    5. 8-RES_FS12288-JB
    6. 10785
    Prev
    Next
    INDEX
    Explanations

    locations and political 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_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.17
    0.8%
    327
    +0.09
    0.4%
    157
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.17
    0.11
    720
    +0.09
    0.11
    327
    +0.09
    0.10
    Negative Logits
     decomp
    -0.73
     jog
    -0.73
     filler
    -0.71
     vulner
    -0.70
     hitch
    -0.67
     fert
    -0.67
     readings
    -0.67
     whiff
    -0.67
     chained
    -0.66
     miscar
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.04
    iversary
    0.94
    HQ
    0.90
    tre
    0.89
    SHIP
    0.86
    ship
    0.85
    Department
    0.84
    owned
    0.82
    CEO
    0.81
    owners
    0.79
    Activations Density 0.401%

    No Known Activations