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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1200
    Prev
    Next
    INDEX
    Explanations

    information related to technology and urban development initiatives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    7
    +0.11
    0.5%
    594
    +0.10
    0.5%
    368
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.11
    0.11
    102
    +0.10
    0.14
    368
    +0.10
    0.10
    Negative Logits
     Pension
    -0.76
     Tours
    -0.67
     UID
    -0.64
    ardy
    -0.63
    Syrian
    -0.63
    ONDON
    -0.62
    ivan
    -0.62
     Doe
    -0.61
    oute
    -0.61
     Coral
    -0.60
    POSITIVE LOGITS
     everywhere
    1.06
     inherently
    1.05
     intrinsically
    1.01
     predominant
    0.97
     synonymous
    0.94
     pervasive
    0.94
     ubiquitous
    0.93
     prevalent
    0.93
     rife
    0.93
     traditionally
    0.92
    Activations Density 3.811%

    No Known Activations