© 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 49152
    9. 8-RES_FS49152-JB
    11. 37041
    Prev
    Next
    INDEX
    Explanations

    words that convey a sense of inadequacy or worthlessness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.12
    0.6%
    481
    +0.11
    0.5%
    722
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    722
    +0.12
    0.01
    404
    +0.11
    0.01
    151
    +0.11
    0.01
    Negative Logits
    aeper
    -0.76
    MER
    -0.70
    udeb
    -0.68
     accur
    -0.68
    asonic
    -0.67
    ickr
    -0.64
    Lago
    -0.64
    omez
    -0.62
     hemor
    -0.62
    =-=-=-=-
    -0.62
    POSITIVE LOGITS
    ness
    1.67
    ly
    1.49
    nesses
    1.44
    liness
    1.12
    NESS
    1.08
    iveness
    0.96
    soever
    0.94
    iate
    0.93
    ity
    0.92
    edly
    0.92
    Activations Density 0.010%

    No Known Activations