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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8295
    Prev
    Next
    INDEX
    Explanations

    phrases related to community projects and 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_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
    480
    +0.29
    1.4%
    447
    +0.20
    1.0%
    457
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.29
    -0.01
    563
    +0.20
    0.06
    598
    +0.13
    0.03
    Negative Logits
    umably
    -0.72
    emate
    -0.71
     Presumably
    -0.70
    Fake
    -0.70
     messing
    -0.68
    udo
    -0.67
     Apparently
    -0.67
    lol
    -0.66
     Oops
    -0.66
    ascal
    -0.65
    POSITIVE LOGITS
     strives
    0.86
     integrates
    0.82
     culmin
    0.81
     curated
    0.80
     motto
    0.79
     explores
    0.79
     innovative
    0.78
     collabor
    0.78
     invaluable
    0.78
     pioneering
    0.78
    Activations Density 1.007%

    No Known Activations