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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43256
    Prev
    Next
    INDEX
    Explanations

    references to immigration and related policies

    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
    575
    +0.14
    0.6%
    288
    +0.14
    0.6%
    343
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.14
    0.03
    343
    +0.14
    0.02
    439
    +0.12
    0.02
    Negative Logits
    sonian
    -0.92
    ilts
    -0.87
    çͰ
    -0.81
    olls
    -0.81
    @#&
    -0.79
    Ü
    -0.78
    oeuv
    -0.74
    idges
    -0.73
    beit
    -0.73
    MpServer
    -0.72
    POSITIVE LOGITS
     detention
    1.06
     reform
    0.98
     enforcement
    0.94
     policy
    0.91
     immigration
    0.89
     crackdown
    0.87
    policy
    0.87
     deportation
    0.86
     policies
    0.86
     visas
    0.86
    Activations Density 0.014%

    No Known Activations