© 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. 10188
    Prev
    Next
    INDEX
    Explanations

    phrases related to job applications and rejections

    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
    447
    +0.14
    0.7%
    654
    +0.10
    0.5%
    10
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.14
    0.07
    654
    +0.10
    0.04
    10
    +0.10
    0.05
    Negative Logits
    raint
    -0.70
    scl
    -0.65
     Caps
    -0.64
    gang
    -0.63
     Canad
    -0.61
     Sanct
    -0.60
    velt
    -0.60
    stead
    -0.60
    rid
    -0.59
    icka
    -0.59
    POSITIVE LOGITS
     applicants
    1.09
     bids
    1.06
     bidder
    0.96
     submissions
    0.96
     bidding
    0.94
     elig
    0.94
    Applic
    0.93
    submit
    0.89
     vying
    0.89
     finalists
    0.88
    Activations Density 0.567%

    No Known Activations