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. 23508
    Prev
    Next
    INDEX
    Explanations

    references to publishing success and major media recognition in the context of literature and music

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.20
    0.9%
    225
    +0.10
    0.5%
    669
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.20
    0.02
    76
    +0.10
    0.05
    225
    +0.10
    0.05
    Negative Logits
     recess
    -0.70
     diseng
    -0.68
     Utt
    -0.66
     holster
    -0.65
    Args
    -0.65
    zik
    -0.64
    stretched
    -0.64
    iencies
    -0.63
    xit
    -0.62
     Symptoms
    -0.61
    POSITIVE LOGITS
     celebrity
    1.15
     fame
    1.13
     Playboy
    1.11
     bestselling
    1.09
     magazines
    1.05
     tabloid
    1.05
     mogul
    1.05
     celebrities
    1.03
     merch
    1.03
     synd
    1.02
    Activations Density 0.689%

    No Known Activations