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. 2764
    Prev
    Next
    INDEX
    Explanations

    interest and activity in economic and financial matters

    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
    634
    +0.13
    0.6%
    195
    +0.13
    0.6%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    634
    +0.13
    0.05
    195
    +0.13
    0.02
    247
    +0.10
    0.04
    Negative Logits
    llan
    -0.78
    rome
    -0.68
    ework
    -0.65
    pex
    -0.63
    女
    -0.63
    aan
    -0.63
    åī
    -0.60
    ELF
    -0.59
    kus
    -0.59
     Kardashian
    -0.59
    POSITIVE LOGITS
    ocene
    0.75
    awaru
    0.74
    edIn
    0.71
     rate
    0.70
     Rate
    0.68
     Interest
    0.68
    uates
    0.68
    ãĥĦ
    0.68
    ties
    0.67
    oscope
    0.67
    Activations Density 0.631%

    No Known Activations