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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11400
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    373
    +0.15
    0.8%
    517
    +0.10
    0.5%
    23
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.15
    0.01
    194
    +0.10
    0.01
    716
    +0.10
    0.01
    Negative Logits
    cil
    -0.64
    terness
    -0.63
     Inher
    -0.62
    arks
    -0.61
    liga
    -0.60
    steen
    -0.60
    ktop
    -0.59
    rans
    -0.59
     Galile
    -0.57
    itialized
    -0.56
    POSITIVE LOGITS
     inbox
    0.90
     newsletters
    0.80
     alerts
    0.78
     newsletter
    0.77
    ads
    0.77
     address
    0.76
     Subscribe
    0.76
     subscribers
    0.74
     Newsletter
    0.70
    email
    0.70
    Activations Density 0.014%

    No Known Activations