© 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. 6847
    Prev
    Next
    INDEX
    Explanations

    information related to naval rescues or maritime incidents

    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
    480
    +0.36
    1.9%
    373
    +0.12
    0.7%
    694
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.36
    -0.01
    694
    +0.12
    0.03
    260
    +0.09
    0.06
    Negative Logits
     congr
    -0.57
     uniqueness
    -0.56
     devs
    -0.54
     wonderful
    -0.54
     folks
    -0.52
     recognizes
    -0.52
     ðŁij
    -0.51
     MFT
    -0.49
    aurus
    -0.49
     EVERY
    -0.48
    POSITIVE LOGITS
    acas
    0.67
     gunfire
    0.62
    oxic
    0.56
    itored
    0.56
     evacuation
    0.55
    interstitial
    0.55
     makeshift
    0.54
    angering
    0.53
    hetamine
    0.52
    airo
    0.52
    Activations Density 1.279%

    No Known Activations