© 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. 18306
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal implications and regulations

    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
    678
    +0.12
    0.6%
    461
    +0.12
    0.5%
    33
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.12
    0.04
    283
    +0.12
    0.01
    724
    +0.11
    0.04
    Negative Logits
     Cosponsors
    -0.74
     Learning
    -0.63
    atform
    -0.63
     Emails
    -0.62
    acting
    -0.62
    illance
    -0.60
     UNCLASSIFIED
    -0.60
     ACTIONS
    -0.60
     organizing
    -0.58
     Zeit
    -0.58
    POSITIVE LOGITS
     cutoff
    0.96
     achievable
    0.92
    Maximum
    0.90
     equate
    0.87
     suffice
    0.86
    elsius
    0.84
     threshold
    0.82
     maximum
    0.81
     corresponds
    0.81
     increments
    0.80
    Activations Density 0.420%

    No Known Activations