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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26134
    Prev
    Next
    INDEX
    Explanations

    emotions and states of being, particularly those related to intoxication and feelings of loss or luck

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.15
    0.7%
    665
    +0.13
    0.6%
    37
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.15
    0.04
    351
    +0.13
    0.03
    70
    +0.10
    0.03
    Negative Logits
    orney
    -0.74
    roma
    -0.70
     testament
    -0.65
    audi
    -0.63
     entirety
    -0.63
    WB
    -0.61
    ofer
    -0.61
    ibia
    -0.61
    ellen
    -0.59
    eatures
    -0.59
    POSITIVE LOGITS
    retty
    0.77
     sidx
    0.76
    quished
    0.74
    */(
    0.71
     quicker
    0.69
     traction
    0.68
    ãĤ¼
    0.68
    ãħĭãħĭ
    0.67
    ptin
    0.64
    rier
    0.64
    Activations Density 0.064%

    No Known Activations