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 24576
    5. 8-RES_FS24576-JB
    6. 23407
    Prev
    Next
    INDEX
    Explanations

    terms related to color and safety

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.13
    0.6%
    491
    +0.10
    0.5%
    526
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.13
    0.02
    288
    +0.10
    0.06
    251
    +0.09
    0.04
    Negative Logits
     awoke
    -0.64
    kson
    -0.61
    AMI
    -0.60
    agine
    -0.59
     Mystic
    -0.58
     Normandy
    -0.58
    itars
    -0.57
     Noir
    -0.55
     Incarnation
    -0.54
    imar
    -0.54
    POSITIVE LOGITS
    lining
    0.72
     guiActiveUn
    0.72
    ãĥij
    0.69
    bench
    0.69
    ãĤ§
    0.67
    ãĤ©
    0.67
    tight
    0.64
     fide
    0.64
    lists
    0.64
    Wallet
    0.63
    Activations Density 0.364%

    No Known Activations