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. 8247
    Prev
    Next
    INDEX
    Explanations

    phrases related to marijuana legalization and its implications, including taxation and government expenditure

    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
    +0.10
    0.5%
    427
    +0.10
    0.5%
    717
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.10
    0.05
    393
    +0.10
    0.05
    717
    +0.10
    0.04
    Negative Logits
    ouls
    -0.76
    stones
    -0.73
    lich
    -0.73
    dan
    -0.72
    TW
    -0.72
    cients
    -0.71
    Brit
    -0.69
    WF
    -0.69
    kees
    -0.68
     Loren
    -0.68
    POSITIVE LOGITS
     dissemination
    1.28
     retention
    1.26
     reproduction
    1.23
     retrieval
    1.23
     disposal
    1.21
     destruction
    1.18
     processing
    1.11
     acquisition
    1.11
     distribution
    1.10
     consumption
    1.09
    Activations Density 0.225%

    No Known Activations