© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    information related to companies, specifically their history and products

    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
    481
    +0.44
    2.7%
    447
    +0.29
    1.8%
    497
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.44
    0.13
    756
    +0.29
    -0.05
    351
    +0.17
    0.04
    Negative Logits
    cigarettes
    -0.66
     Canaver
    -0.62
    ':
    -0.53
    ãĤ¨ãĥ«
    -0.49
    \":
    -0.48
    awed
    -0.47
     Guant
    -0.46
     Tsarnaev
    -0.46
     âĵĺ
    -0.45
    cigarette
    -0.45
    POSITIVE LOGITS
     withd
    0.56
     dilig
    0.55
     utilized
    0.49
     referen
    0.47
     utilize
    0.46
     livest
    0.45
     utilizing
    0.45
     incorpor
    0.45
    .""
    0.44
     thru
    0.44
    Activations Density 2.318%

    No Known Activations