© 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 24576
    9. 8-RES_FS24576-JB
    11. 18828
    Prev
    Next
    INDEX
    Explanations

    references to legal actions or issues related to mortgages and property ownership

    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
    104
    +0.12
    0.5%
    447
    +0.11
    0.5%
    151
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.02
    575
    +0.11
    0.02
    104
    +0.11
    0.02
    Negative Logits
    orie
    -0.76
    ceed
    -0.72
    wra
    -0.71
    rams
    -0.71
    leon
    -0.71
    gio
    -0.70
    OTUS
    -0.70
    Translation
    -0.69
    eworthy
    -0.68
    resso
    -0.67
    POSITIVE LOGITS
     homeowners
    0.94
     evict
    0.82
     homeowner
    0.82
     associations
    0.81
     beware
    0.81
     association
    0.80
    hip
    0.79
     tenant
    0.78
     intruder
    0.74
     tenants
    0.70
    Activations Density 0.035%

    No Known Activations