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 3072
    5. 8-RES_FS3072-JB
    6. 1997
    Prev
    Next
    INDEX
    Explanations

    legal charges and criminal activities related to hacking and fraud

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    385
    +0.10
    0.5%
    288
    +0.09
    0.4%
    316
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.10
    0.06
    386
    +0.09
    0.05
    268
    +0.09
    0.03
    Negative Logits
    ARCH
    -0.84
     livest
    -0.71
    ullivan
    -0.66
    Unit
    -0.66
    orph
    -0.64
    skill
    -0.64
    estate
    -0.64
    icz
    -0.63
    perm
    -0.63
    Redd
    -0.63
    POSITIVE LOGITS
    heet
    1.22
     levied
    0.92
     charges
    0.86
     sheet
    0.78
     Charges
    0.78
    llah
    0.78
     leve
    0.77
    sheet
    0.76
     leveled
    0.76
    hyde
    0.75
    Activations Density 0.598%

    No Known Activations