© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 21982
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and updates

    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
    87
    +0.20
    1.0%
    464
    +0.15
    0.8%
    756
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.20
    -0.03
    756
    +0.15
    -0.03
    655
    +0.11
    0.04
    Negative Logits
    NetMessage
    -0.79
     Flavoring
    -0.71
    ]."
    -0.68
    )].
    -0.63
    '."
    -0.60
    ."[
    -0.59
    "/>
    -0.59
    )",
    -0.58
    ]).
    -0.57
    unts
    -0.57
    POSITIVE LOGITS
    iversary
    0.80
     congratulations
    0.71
     followed
    0.66
     congr
    0.66
     reception
    0.65
    ãĥ¼ãĥ³
    0.63
     predecessor
    0.62
    sequent
    0.62
     initially
    0.60
     preceded
    0.60
    Activations Density 0.973%

    No Known Activations