Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11392
    Prev
    Next
    INDEX
    Explanations

    large numerical values or figures

    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
    169
    +0.12
    0.6%
    230
    +0.11
    0.5%
    63
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.12
    0.05
    63
    +0.11
    0.04
    471
    +0.11
    0.04
    Negative Logits
    ifice
    -0.74
    ivity
    -0.69
    krit
    -0.68
    iqu
    -0.66
    rival
    -0.66
    ournal
    -0.63
    venge
    -0.63
    ufact
    -0.63
    otto
    -0.63
    agon
    -0.61
    POSITIVE LOGITS
    +
    1.07
    Hz
    1.06
    mAh
    1.03
    bps
    0.94
     Hz
    0.93
     lbs
    0.88
    lb
    0.87
     miles
    0.87
     ppm
    0.87
    ths
    0.87
    Activations Density 0.077%

    No Known Activations