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. 1488
    Prev
    Next
    INDEX
    Explanations

    phrases related to replacing something or someone

    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
    213
    +0.10
    0.5%
    143
    +0.10
    0.4%
    166
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.10
    0.04
    288
    +0.10
    0.05
    329
    +0.10
    0.03
    Negative Logits
    raq
    -1.00
    insula
    -0.76
    jah
    -0.71
    ggle
    -0.69
    hest
    -0.68
    about
    -0.66
    osis
    -0.66
    akra
    -0.66
    ostic
    -0.65
     isEnabled
    -0.65
    POSITIVE LOGITS
    ments
    0.80
    atives
    0.79
     scratch
    0.75
    manent
    0.75
     retiring
    0.74
    mented
    0.73
     redundant
    0.73
     obsolete
    0.72
    oreal
    0.72
    ative
    0.70
    Activations Density 0.712%

    No Known Activations