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. 23450
    Prev
    Next
    INDEX
    Explanations

    references to creationism

    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
    459
    +0.13
    0.6%
    642
    +0.12
    0.5%
    414
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.13
    0.02
    212
    +0.12
    0.02
    414
    +0.10
    0.01
    Negative Logits
    EGA
    -0.74
    phia
    -0.70
     Ago
    -0.67
     lob
    -0.64
    olulu
    -0.64
     Caf
    -0.64
     Mahar
    -0.63
    RESULTS
    -0.63
     nerves
    -0.63
     Fulton
    -0.62
    POSITIVE LOGITS
    ivist
    0.94
    ivism
    0.89
    ism
    0.86
    ist
    0.82
    idable
    0.81
    smanship
    0.80
    ally
    0.80
    istically
    0.78
    emis
    0.78
    flags
    0.77
    Activations Density 0.036%

    No Known Activations