© 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. 7888
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or activities, especially those involving movement and exploration

    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
    718
    +0.14
    0.7%
    49
    +0.11
    0.5%
    658
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.14
    0.07
    49
    +0.11
    0.07
    608
    +0.10
    0.07
    Negative Logits
    ieth
    -0.63
    woman
    -0.61
     trademarks
    -0.58
    verages
    -0.58
    typ
    -0.58
    regulation
    -0.58
     Opinion
    -0.58
    Got
    -0.58
    ively
    -0.57
     Decision
    -0.56
    POSITIVE LOGITS
     accompany
    1.14
     commemorate
    1.14
     relieve
    1.13
     satisfy
    1.13
     counteract
    1.13
     replace
    1.12
     bolster
    1.09
     facilitate
    1.08
     compensate
    1.07
     fulfill
    1.06
    Activations Density 0.209%

    No Known Activations