Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2463
    Prev
    Next
    INDEX
    Explanations

    technical details and descriptions of physical structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    233
    +0.13
    0.6%
    81
    +0.12
    0.6%
    84
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.13
    0.08
    191
    +0.12
    0.05
    720
    +0.11
    0.07
    Negative Logits
    Rat
    -0.64
    ĸļ
    -0.63
    interstitial
    -0.63
    itialized
    -0.63
    answered
    -0.62
    ŃĶ
    -0.62
     Became
    -0.61
    »Ĵ
    -0.60
    é¾
    -0.59
    ãĥ¤
    -0.59
    POSITIVE LOGITS
     but
    1.47
    but
    1.33
     nor
    1.21
     But
    1.09
     BUT
    1.08
    But
    1.07
    although
    0.95
    though
    0.92
     though
    0.86
     However
    0.84
    Activations Density 1.989%

    No Known Activations