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. 1485
    Prev
    Next
    INDEX
    Explanations

    countries and locations

    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
    481
    +0.16
    0.7%
    67
    +0.15
    0.7%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.16
    0.15
    57
    +0.15
    0.10
    461
    +0.12
    0.09
    Negative Logits
    tops
    -0.66
    Sym
    -0.65
    hide
    -0.62
     RTX
    -0.60
    atin
    -0.60
    Discussion
    -0.59
     Weiner
    -0.59
    TY
    -0.58
    iple
    -0.58
    veyard
    -0.57
    POSITIVE LOGITS
     Airlines
    0.97
     Today
    0.88
    's
    0.85
     TODAY
    0.84
     Yard
    0.83
     invaded
    0.81
     Arabia
    0.77
     annexed
    0.75
    borg
    0.74
     Aerospace
    0.74
    Activations Density 0.782%

    No Known Activations