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

    Neuronpedia

    Jacobian LensNEW
    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. 9142
    Prev
    Next
    INDEX
    Explanations

    phrases related to dependency and being dependent on certain entities or systems

    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
    97
    +0.13
    0.6%
    288
    +0.11
    0.5%
    146
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.13
    0.01
    125
    +0.11
    0.01
    311
    +0.10
    0.01
    Negative Logits
    efer
    -0.85
    mberg
    -0.78
    itz
    -0.77
    ific
    -0.75
    ²¾
    -0.75
    tein
    -0.73
    ulton
    -0.71
    sell
    -0.71
    unci
    -0.70
    furt
    -0.69
    POSITIVE LOGITS
    encies
    0.94
     upon
    0.81
    ency
    0.78
     dependency
    0.76
    doms
    0.75
     liability
    0.69
     reliant
    0.68
    ministic
    0.68
     cooker
    0.67
     dependence
    0.66
    Activations Density 0.034%

    No Known Activations