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. 1208
    Prev
    Next
    INDEX
    Explanations

    sentences starting with the word "So"

    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
    240
    +0.14
    0.7%
    715
    +0.12
    0.6%
    559
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.14
    0.08
    598
    +0.12
    0.06
    559
    +0.10
    0.06
    Negative Logits
    saf
    -0.73
    thro
    -0.64
     nic
    -0.60
    sk
    -0.58
    exclusive
    -0.57
     Purg
    -0.57
     Halls
    -0.56
    degree
    -0.56
    ski
    -0.56
    âĹ¼
    -0.55
    POSITIVE LOGITS
    oner
    1.31
    bered
    1.09
    fter
    1.07
    FTWARE
    1.04
    apy
    1.02
    ooo
    0.96
    oths
    0.96
    othes
    0.95
     far
    0.92
    aring
    0.90
    Activations Density 0.228%

    No Known Activations