© 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. 107
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs indicating speech or actions

    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
    316
    +0.13
    0.6%
    719
    +0.11
    0.5%
    121
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.13
    0.05
    719
    +0.11
    0.05
    612
    +0.11
    0.04
    Negative Logits
    noon
    -0.81
    etheless
    -0.72
    acters
    -0.70
    rocket
    -0.69
    Operation
    -0.63
    evidence
    -0.61
     fractions
    -0.61
     totality
    -0.61
    selection
    -0.59
     menstrual
    -0.58
    POSITIVE LOGITS
     said
    1.42
     wrote
    1.34
     says
    1.26
    said
    1.16
     explained
    1.13
     joked
    1.13
     tweeted
    1.13
     exclaimed
    1.12
     told
    1.11
     replied
    1.08
    Activations Density 0.055%

    No Known Activations