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

    Neuronpedia

    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. 8558
    Prev
    Next
    INDEX
    Explanations

    specific words related to professional responsibilities and ethical considerations

    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
    377
    +0.12
    0.5%
    724
    +0.11
    0.5%
    542
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    542
    +0.12
    0.06
    540
    +0.11
    0.06
    724
    +0.11
    0.06
    Negative Logits
    ancies
    -0.73
    onyms
    -0.67
    iries
    -0.66
    dimension
    -0.66
    undreds
    -0.66
    obos
    -0.66
    verning
    -0.65
    irie
    -0.64
     roofs
    -0.64
    racuse
    -0.63
    POSITIVE LOGITS
     considering
    1.15
     indeed
    1.11
     nonetheless
    1.06
     compared
    0.94
     behold
    0.80
     imaginable
    0.77
    stros
    0.73
     nevertheless
    0.70
     akin
    0.70
     worth
    0.68
    Activations Density 0.248%

    No Known Activations