Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 619
    Prev
    Next
    INDEX
    Explanations

    references to critiques of political figures or policies

    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
    +0.19
    0.9%
    756
    +0.13
    0.6%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.19
    0.07
    285
    +0.13
    0.07
    640
    +0.11
    0.12
    Negative Logits
    agar
    -0.67
    onica
    -0.64
    original
    -0.62
    ction
    -0.59
    iatus
    -0.58
    abe
    -0.56
    rising
    -0.55
    rique
    -0.55
    Lex
    -0.54
    çīĪ
    -0.53
    POSITIVE LOGITS
     etc
    1.25
    etc
    1.23
     Lastly
    1.07
    Lastly
    0.85
     Finally
    0.82
     blah
    0.73
     };
    0.72
     ect
    0.69
    Finally
    0.66
    CONCLUS
    0.65
    Activations Density 1.967%

    No Known Activations