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. 21940
    Prev
    Next
    INDEX
    Explanations

    the word "remaining" followed by a number

    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
    402
    +0.13
    0.6%
    195
    +0.10
    0.4%
    223
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.13
    0.02
    223
    +0.10
    0.02
    153
    +0.09
    0.01
    Negative Logits
    gui
    -0.77
    gio
    -0.74
    sych
    -0.70
    kaya
    -0.68
    cause
    -0.68
    omed
    -0.67
    mbol
    -0.67
    imaru
    -0.67
    gemony
    -0.66
    gging
    -0.64
    POSITIVE LOGITS
     remnants
    0.87
     portions
    0.87
     intact
    0.86
     undecided
    0.86
     remaining
    0.85
     segments
    0.83
     remnant
    0.83
     sections
    0.82
     fractions
    0.82
     installments
    0.80
    Activations Density 0.027%

    No Known Activations