© 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 12288
    9. 8-RES_FS12288-JB
    11. 1352
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating possession

    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
    362
    +0.12
    0.6%
    617
    +0.12
    0.5%
    92
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.11
    92
    +0.12
    0.07
    617
    +0.12
    0.07
    Negative Logits
    ibaba
    -0.79
    uve
    -0.77
    ciation
    -0.77
    haus
    -0.74
    ocument
    -0.73
    vine
    -0.72
     along
    -0.72
    river
    -0.65
     largeDownload
    -0.65
    forth
    -0.65
    POSITIVE LOGITS
     own
    1.73
    self
    1.58
    selves
    1.38
     surroundings
    1.34
     peers
    1.30
     superiors
    1.19
     OWN
    1.15
     neighbour
    1.13
     fellow
    1.13
    elf
    1.12
    Activations Density 0.428%

    No Known Activations