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 49152
    5. 8-RES_FS49152-JB
    6. 12101
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to competitive events or contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    735
    +0.09
    0.4%
    333
    +0.09
    0.4%
    24
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.09
    0.01
    577
    +0.09
    0.01
    622
    +0.08
    0.01
    Negative Logits
    enegger
    -0.91
    ufact
    -0.71
    htaking
    -0.67
    atari
    -0.64
    oppable
    -0.62
    soDeliveryDate
    -0.60
    eki
    -0.59
    ĸļ
    -0.59
     elector
    -0.59
    atcher
    -0.59
    POSITIVE LOGITS
    ©¶æ
    0.75
    Fine
    0.68
    bilt
    0.66
     Nex
    0.66
     Vega
    0.66
    Sov
    0.65
    IUM
    0.64
    Mobil
    0.63
    Prev
    0.62
    ronic
    0.62
    Activations Density 0.034%

    No Known Activations