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. 2805
    Prev
    Next
    INDEX
    Explanations

    information related to police reports and criminal activities

    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
    373
    +0.14
    0.6%
    507
    +0.10
    0.5%
    430
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.14
    0.09
    693
    +0.10
    0.09
    260
    +0.10
    0.08
    Negative Logits
    Reviewer
    -0.77
     Definitive
    -0.69
    eries
    -0.68
     Compar
    -0.63
     Parables
    -0.63
    channelAvailability
    -0.62
     guiIcon
    -0.61
     comparisons
    -0.61
     Haku
    -0.60
     dearly
    -0.60
    POSITIVE LOGITS
    pm
    1.30
     noon
    1.21
    noon
    1.14
    PM
    1.09
     midday
    1.09
     pm
    1.06
     midnight
    1.02
    onday
    0.98
     hrs
    0.91
    aturdays
    0.91
    Activations Density 0.697%

    No Known Activations