© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19635
    Prev
    Next
    INDEX
    Explanations

    phrases related to having or gaining access to something

    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
    365
    +0.11
    0.5%
    288
    +0.10
    0.4%
    688
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.11
    0.03
    365
    +0.10
    0.02
    688
    +0.09
    0.02
    Negative Logits
     Kern
    -0.84
     farewell
    -0.65
     Jou
    -0.60
    Maker
    -0.58
     almond
    -0.58
     disband
    -0.57
     Goodbye
    -0.57
     bulls
    -0.56
     Saud
    -0.55
     Empires
    -0.55
    POSITIVE LOGITS
    ibility
    1.36
    ibly
    1.32
    ible
    1.14
    ioned
    1.01
     thereto
    0.95
    ibilities
    0.95
    ibl
    0.93
    ãĥ¼ãĥĨ
    0.89
    ion
    0.88
    ibles
    0.86
    Activations Density 0.025%

    No Known Activations