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. 26109
    Prev
    Next
    INDEX
    Explanations

    instances of the word "overcome" in various contexts

    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
    57
    +0.10
    0.5%
    608
    +0.10
    0.5%
    375
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.10
    0.01
    375
    +0.10
    0.01
    312
    +0.10
    0.01
    Negative Logits
    dot
    -0.75
    cas
    -0.75
    dar
    -0.74
    abet
    -0.74
    responsible
    -0.72
     contrace
    -0.71
    pring
    -0.71
    asus
    -0.71
    exempt
    -0.70
    audi
    -0.70
    POSITIVE LOGITS
     obstacles
    1.25
     adversity
    1.13
     hurdles
    1.06
     difficulties
    1.03
     misconceptions
    0.97
     weaknesses
    0.95
     hurdle
    0.95
     barriers
    0.94
     prejudice
    0.92
     deficiencies
    0.89
    Activations Density 0.015%

    No Known Activations