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. 2802
    Prev
    Next
    INDEX
    Explanations

    references to art or artistic elements

    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
    339
    +0.11
    0.5%
    14
    +0.11
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.07
    575
    +0.11
    0.06
    414
    +0.10
    0.04
    Negative Logits
     htt
    -0.77
     iod
    -0.69
     XT
    -0.67
     Wyoming
    -0.66
     DN
    -0.65
     Nets
    -0.62
    KI
    -0.61
     Telecommunications
    -0.61
    inki
    -0.61
     Laden
    -0.60
    POSITIVE LOGITS
    isans
    1.53
    emis
    1.44
    istry
    1.42
    esian
    1.35
    isan
    1.27
    ifacts
    1.20
    illery
    1.19
    ifice
    1.18
    works
    1.14
    ificial
    1.05
    Activations Density 0.741%

    No Known Activations