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. 8473
    Prev
    Next
    INDEX
    Explanations

    locations or buildings with specific mentions of 'ritz'

    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
    649
    +0.12
    0.5%
    494
    +0.12
    0.5%
    526
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    494
    +0.12
    0.02
    700
    +0.12
    0.01
    Negative Logits
     Pradesh
    -0.69
    selves
    -0.69
    ACTED
    -0.67
     synonymous
    -0.66
     occas
    -0.65
    åŃ
    -0.62
     awa
    -0.61
     readable
    -0.61
     offence
    -0.61
     Thumbnails
    -0.60
    POSITIVE LOGITS
    gerald
    1.70
    sch
    1.23
    patrick
    1.13
    heimer
    1.06
    enger
    1.03
    mann
    1.00
    geist
    0.98
    ky
    0.96
    hou
    0.96
    itz
    0.95
    Activations Density 0.020%

    No Known Activations