© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 765
    Prev
    Next
    INDEX
    Explanations

    ages or terms indicating age difference between individuals, primarily focusing on comparisons involving the term "younger."

    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
    709
    +0.11
    0.5%
    288
    +0.11
    0.5%
    132
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.11
    0.03
    571
    +0.11
    0.03
    132
    +0.10
    0.03
    Negative Logits
    orial
    -0.76
    election
    -0.73
    upuncture
    -0.71
    utterstock
    -0.68
    itars
    -0.66
    plain
    -0.66
    odor
    -0.66
    square
    -0.65
    exec
    -0.65
    tra
    -0.64
    POSITIVE LOGITS
     sibling
    1.42
     generations
    1.25
     brother
    1.23
     versions
    1.23
     sister
    1.19
     siblings
    1.18
     than
    1.09
     generation
    0.99
     version
    0.98
     cousin
    0.95
    Activations Density 0.074%

    No Known Activations