© 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. 8951
    Prev
    Next
    INDEX
    Explanations

    verbs related to negative effects or consequences

    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
    314
    +0.12
    0.5%
    45
    +0.12
    0.5%
    167
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.05
    643
    +0.12
    0.03
    301
    +0.11
    0.03
    Negative Logits
     sidx
    -0.66
    cius
    -0.62
     injunction
    -0.57
     Pwr
    -0.57
     bang
    -0.57
     stead
    -0.56
     Sina
    -0.55
     crawl
    -0.55
     Om
    -0.54
     Observer
    -0.52
    POSITIVE LOGITS
    ing
    2.57
    ed
    1.33
    ions
    1.29
    edIn
    1.25
    ING
    1.21
    ively
    1.19
    ment
    1.18
    ingly
    1.17
    ging
    1.17
    ation
    1.16
    Activations Density 0.197%

    No Known Activations