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. 43291
    Prev
    Next
    INDEX
    Explanations

    expressions related to mortality and dying

    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
    152
    +0.13
    0.6%
    666
    +0.10
    0.5%
    727
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.13
    0.03
    639
    +0.10
    0.02
    482
    +0.10
    0.02
    Negative Logits
     Cosponsors
    -0.66
    eele
    -0.66
    ERSON
    -0.61
     Droid
    -0.61
     boundaries
    -0.60
     showc
    -0.57
    £ı
    -0.56
    achine
    -0.56
     IC
    -0.56
     [+
    -0.56
    POSITIVE LOGITS
    eat
    0.90
    hard
    0.89
    thro
    0.87
    cycle
    0.79
    stroke
    0.78
    bolt
    0.77
    gone
    0.77
    blers
    0.76
    dead
    0.74
    obos
    0.74
    Activations Density 0.027%

    No Known Activations