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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9059
    Prev
    Next
    INDEX
    Explanations

    the negation of statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    102
    +0.14
    0.7%
    496
    +0.10
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.14
    0.05
    566
    +0.10
    0.04
    643
    +0.10
    0.03
    Negative Logits
    cano
    -0.80
    å¥
    -0.78
     peaks
    -0.72
    alez
    -0.70
    ounters
    -0.69
    inav
    -0.65
    ð
    -0.64
    iox
    -0.64
     emerges
    -0.64
    çļ
    -0.63
    POSITIVE LOGITS
     kidding
    1.21
     interested
    1.21
     bothered
    1.17
     afraid
    1.16
     aware
    1.15
     ashamed
    1.11
     gonna
    1.11
     amused
    1.10
     necessarily
    1.08
     able
    1.03
    Activations Density 0.096%

    No Known Activations