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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 885
    Prev
    Next
    INDEX
    Explanations

    events related to chaotic situations or violence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    326
    +0.12
    0.5%
    201
    +0.11
    0.5%
    599
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.14
    70
    +0.11
    0.13
    526
    +0.10
    0.01
    Negative Logits
    éĸ
    -0.94
    ĻĤ
    -0.71
    ItemImage
    -0.67
    quickShipAvailable
    -0.66
    OTOS
    -0.65
     Loan
    -0.64
    Ct
    -0.64
     Liberties
    -0.62
     latitude
    -0.62
    æ©Ł
    -0.62
    POSITIVE LOGITS
     uncontroll
    1.17
    ishly
    0.98
     havoc
    0.93
    ingly
    0.90
     inco
    0.89
     hyster
    0.89
     wildly
    0.88
     loudly
    0.88
     furiously
    0.86
     louder
    0.83
    Activations Density 2.695%

    No Known Activations