© 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 24576
    5. 8-RES_FS24576-JB
    6. 6625
    Prev
    Next
    INDEX
    Explanations

    references to crime scenes and criminal activities

    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
    640
    +0.24
    1.1%
    480
    +0.19
    0.9%
    447
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.24
    0.10
    640
    +0.19
    0.09
    679
    +0.17
    0.08
    Negative Logits
     contingency
    -0.78
     affili
    -0.69
     nodd
    -0.68
    iqueness
    -0.68
     qualitative
    -0.68
    iation
    -0.68
     biological
    -0.67
     challeng
    -0.67
     education
    -0.66
    ledged
    -0.66
    POSITIVE LOGITS
    jpg
    1.18
     Seems
    1.03
    gif
    1.01
    wav
    0.98
     Includes
    0.98
     Featuring
    0.96
    png
    0.95
     Looks
    0.95
     Allows
    0.94
     Luckily
    0.92
    Activations Density 0.317%

    No Known Activations