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 1536
    5. 8-RES_FS1536-JB
    6. 196
    Prev
    Next
    INDEX
    Explanations

    government officials, political figures, and world leaders

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    373
    +0.12
    0.5%
    203
    +0.10
    0.5%
    248
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.10
    232
    +0.10
    0.07
    203
    +0.10
    0.06
    Negative Logits
    anwhile
    -0.77
    oldemort
    -0.69
    wark
    -0.66
    pel
    -0.65
    kson
    -0.65
    ascade
    -0.64
    ologies
    -0.64
    ngth
    -0.62
     chalk
    -0.62
    anners
    -0.61
    POSITIVE LOGITS
     ministerial
    1.14
     Minister
    1.13
     minister
    1.09
     ministers
    0.97
     Ministers
    0.92
    knit
    0.90
    val
    0.89
    etime
    0.78
     Rib
    0.71
    ition
    0.70
    Activations Density 1.736%

    No Known Activations