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. 1067
    Prev
    Next
    INDEX
    Explanations

    numeric values

    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
    299
    +0.11
    0.5%
    707
    +0.10
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.11
    0.03
    482
    +0.10
    0.03
    326
    +0.10
    0.02
    Negative Logits
     assumptions
    -0.66
     corrid
    -0.66
     retina
    -0.66
     whisk
    -0.66
     mant
    -0.63
     empowered
    -0.62
     exemptions
    -0.62
     palate
    -0.61
     optimistic
    -0.59
     obsolete
    -0.58
    POSITIVE LOGITS
    soever
    0.87
    nian
    0.87
    hyde
    0.84
    wm
    0.84
    chev
    0.82
    tch
    0.81
    hex
    0.80
    Edit
    0.77
    sum
    0.76
    Ever
    0.75
    Activations Density 0.066%

    No Known Activations