© 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. 448
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing some sort of effect or action

    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
    718
    +0.15
    0.7%
    608
    +0.15
    0.7%
    139
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.15
    0.05
    718
    +0.15
    0.05
    665
    +0.11
    0.04
    Negative Logits
     Klu
    -0.67
     Uses
    -0.64
     Used
    -0.63
    prem
    -0.62
     Kop
    -0.61
     Highest
    -0.61
     Observer
    -0.59
     Newsp
    -0.59
    igm
    -0.59
     Cros
    -0.57
    POSITIVE LOGITS
     improve
    1.25
     alleviate
    1.23
     promote
    1.21
     appease
    1.18
     emulate
    1.17
     conserve
    1.17
     deserve
    1.16
     accommodate
    1.14
     mitigate
    1.13
     enhance
    1.11
    Activations Density 0.174%

    No Known Activations