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. 5532
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and engineering concepts

    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
    159
    +0.11
    0.5%
    447
    +0.11
    0.5%
    588
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.07
    159
    +0.11
    0.05
    588
    +0.10
    0.05
    Negative Logits
    =-=-=-=-
    -0.89
    bright
    -0.78
    adier
    -0.76
    alter
    -0.75
    ãĤ¨ãĥ«
    -0.74
    Snow
    -0.70
    ipedia
    -0.70
    wen
    -0.67
    agi
    -0.67
    ename
    -0.67
    POSITIVE LOGITS
     (>
    0.98
     earners
    0.87
     residential
    0.77
     (<
    0.75
     versions
    0.72
     discretionary
    0.67
     airborne
    0.66
     solutions
    0.66
     recreational
    0.63
     TVs
    0.62
    Activations Density 0.532%

    No Known Activations