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. 19271
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
    690
    +0.10
    0.5%
    255
    +0.10
    0.5%
    307
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.10
    0.04
    30
    +0.10
    0.03
    227
    +0.10
    0.02
    Negative Logits
     sacrific
    -0.81
     behavi
    -0.69
     Juda
    -0.67
     advoc
    -0.65
     fundament
    -0.63
     Dept
    -0.62
    ioch
    -0.61
    mington
    -0.60
    yd
    -0.60
     Til
    -0.59
    POSITIVE LOGITS
     Username
    0.66
    BuyableInstoreAndOnline
    0.65
    orial
    0.64
    unctions
    0.64
     Shia
    0.63
    ippi
    0.62
    iae
    0.62
    geries
    0.61
    ativity
    0.61
    interstitial
    0.60
    Activations Density 0.201%

    No Known Activations