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. 11427
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, in this case, the name "Riley"

    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
    447
    +0.12
    0.6%
    582
    +0.10
    0.4%
    3
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    326
    +0.10
    0.01
    99
    +0.09
    0.01
    Negative Logits
    CRIP
    -0.80
    naire
    -0.76
    EMBER
    -0.75
    dayName
    -0.73
    ktop
    -0.72
    ocre
    -0.72
    atel
    -0.70
    stood
    -0.68
    irements
    -0.66
    ozy
    -0.65
    POSITIVE LOGITS
     Cyrus
    1.11
    boro
    0.81
    gon
    0.79
    croft
    0.77
     Patterson
    0.77
    cock
    0.76
    ancing
    0.73
     Porter
    0.71
    brook
    0.71
    Madison
    0.69
    Activations Density 0.024%

    No Known Activations