© 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. 7484
    Prev
    Next
    INDEX
    Explanations

    instances of words related to computer security and technology

    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
    +0.52
    2.8%
    447
    +0.13
    0.7%
    266
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.01
    266
    +0.13
    0.08
    665
    +0.10
    0.07
    Negative Logits
     Latest
    -0.60
    *:
    -0.56
    orld
    -0.53
     belonged
    -0.53
    includes
    -0.52
     aloud
    -0.51
    ials
    -0.48
    last
    -0.48
     consisted
    -0.48
     preceded
    -0.48
    POSITIVE LOGITS
     equilibrium
    0.66
     unwanted
    0.65
     undesirable
    0.63
     overall
    0.61
    catentry
    0.60
     undue
    0.60
     throughput
    0.60
     unnecessary
    0.60
     future
    0.59
     reuse
    0.58
    Activations Density 0.909%

    No Known Activations