© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 9267
    Prev
    Next
    INDEX
    Explanations

    accumulation or time-related information in text

    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
    375
    +0.12
    0.5%
    447
    +0.11
    0.5%
    487
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.01
    646
    +0.11
    0.01
    724
    +0.10
    0.02
    Negative Logits
    otiation
    -0.91
    inition
    -0.76
    facing
    -0.69
    hift
    -0.69
    word
    -0.69
    jab
    -0.66
    ney
    -0.65
    primary
    -0.65
    Ale
    -0.64
    gnu
    -0.64
    POSITIVE LOGITS
     accumulated
    0.98
     amassed
    0.95
    ulative
    0.86
     piles
    0.85
     wealth
    0.82
    ãĤ¤ãĥĪ
    0.79
     accumulate
    0.78
     accum
    0.77
     riches
    0.74
     debts
    0.74
    Activations Density 0.043%

    No Known Activations