© 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. 7889
    Prev
    Next
    INDEX
    Explanations

    technological and administrative terms related to computer networks and 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
    76
    +0.10
    0.5%
    703
    +0.10
    0.5%
    105
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    703
    +0.10
    0.04
    604
    +0.10
    0.03
    375
    +0.10
    0.02
    Negative Logits
    Ó
    -0.92
    inarily
    -0.91
    iably
    -0.87
    æĺ
    -0.86
    oubtedly
    -0.86
    ptives
    -0.84
    etheless
    -0.83
    ogether
    -0.82
    à¨
    -0.82
    rarily
    -0.82
    POSITIVE LOGITS
     blackout
    0.85
     breaker
    0.78
     exception
    0.77
     HRC
    0.76
     EC
    0.75
     +/-
    0.75
     doesnt
    0.75
     admin
    0.73
     temp
    0.73
     unknown
    0.73
    Activations Density 0.497%

    No Known Activations