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. 7848
    Prev
    Next
    INDEX
    Explanations

    information related to cities, crime rates, and government statistics

    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
    393
    +0.14
    0.6%
    71
    +0.12
    0.5%
    593
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.14
    0.03
    593
    +0.12
    0.03
    5
    +0.11
    0.02
    Negative Logits
    ĸļ
    -0.84
    ername
    -0.78
     srfAttach
    -0.74
    rade
    -0.73
    recy
    -0.73
    ļéĨĴ
    -0.72
    ury
    -0.71
    iquette
    -0.71
    forward
    -0.70
    ĺ
    -0.69
    POSITIVE LOGITS
     entries
    1.01
     occurrences
    1.01
     times
    0.98
     entrants
    0.94
     fatalities
    0.92
     acres
    0.91
     casualties
    0.91
     instances
    0.89
     allowable
    0.89
     deaths
    0.88
    Activations Density 0.045%

    No Known Activations