Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1039
    Prev
    Next
    INDEX
    Explanations

    gender-related words and workplace terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    463
    +0.11
    0.5%
    344
    +0.10
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.12
    344
    +0.10
    0.13
    455
    +0.10
    0.13
    Negative Logits
     Buster
    -0.65
    vich
    -0.65
     Warwick
    -0.64
     Everything
    -0.62
     Corpus
    -0.61
     Byr
    -0.61
     Sandwich
    -0.60
     Lavrov
    -0.60
    RAW
    -0.60
    forcer
    -0.59
    POSITIVE LOGITS
     clustered
    0.80
     perished
    0.80
     individually
    0.77
     outright
    0.76
    eligible
    0.75
     either
    0.74
    ebted
    0.71
     voluntarily
    0.70
     classified
    0.70
     surveyed
    0.70
    Activations Density 3.952%

    No Known Activations