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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11062
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating a sense of belonging or involvement in a group or situation

    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
    92
    +0.10
    0.4%
    430
    +0.09
    0.4%
    296
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    685
    +0.10
    0.02
    341
    +0.09
    0.03
    762
    +0.09
    0.03
    Negative Logits
    orously
    -0.82
    ĸļ
    -0.76
    cru
    -0.70
    ready
    -0.68
    plin
    -0.65
    charg
    -0.65
    itialized
    -0.64
    amaru
    -0.64
    usp
    -0.63
    fried
    -0.63
    POSITIVE LOGITS
     sake
    1.18
     purposes
    1.03
     personally
    1.02
    selves
    0.92
     reasons
    0.89
     liking
    0.85
    self
    0.84
     guys
    0.79
     selves
    0.76
    ummies
    0.70
    Activations Density 0.073%

    No Known Activations