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 6144
    5. 8-RES_FS6144-JB
    6. 5438
    Prev
    Next
    INDEX
    Explanations

    words related to emphasis or certainty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    481
    +0.12
    0.6%
    128
    +0.10
    0.5%
    685
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.12
    0.03
    734
    +0.10
    0.03
    622
    +0.10
    0.03
    Negative Logits
     screenings
    -0.81
     leases
    -0.71
     newsletters
    -0.71
    pta
    -0.67
     postings
    -0.66
    isson
    -0.66
     pige
    -0.66
     belts
    -0.65
    azine
    -0.65
    served
    -0.65
    POSITIVE LOGITS
    initions
    0.83
     altru
    0.81
     believer
    0.78
     grassroots
    0.71
    polit
    0.70
    hero
    0.70
    ĨĴ
    0.69
    é»Ĵ
    0.67
     beginner
    0.67
     fide
    0.66
    Activations Density 0.258%

    No Known Activations