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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10053
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "asylum."

    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
    288
    +0.18
    0.8%
    481
    +0.15
    0.7%
    575
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.03
    575
    +0.15
    0.03
    343
    +0.14
    0.03
    Negative Logits
    Eat
    -0.66
    ideshow
    -0.65
     Hobby
    -0.65
     Toast
    -0.64
     Collider
    -0.63
    uns
    -0.61
    oven
    -0.60
    pread
    -0.59
     Taste
    -0.59
     TEST
    -0.58
    POSITIVE LOGITS
     seeker
    1.37
     seekers
    1.34
     waivers
    0.97
     clearance
    0.91
     versa
    0.91
    ylum
    0.91
     detain
    0.90
     visas
    0.89
     revocation
    0.84
    nesty
    0.84
    Activations Density 0.078%

    No Known Activations