© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7977
    Prev
    Next
    INDEX
    Explanations

    names and terms related to characters and companies

    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
    668
    +0.13
    0.6%
    556
    +0.13
    0.6%
    209
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.13
    0.04
    288
    +0.13
    0.05
    543
    +0.11
    0.03
    Negative Logits
    rez
    -0.97
    rar
    -0.96
    IND
    -0.92
    ERG
    -0.92
    actionDate
    -0.91
    bern
    -0.89
    rea
    -0.86
    deck
    -0.86
    rent
    -0.85
    azel
    -0.82
    POSITIVE LOGITS
     Syndrome
    0.90
     Productions
    0.90
     Massacre
    0.84
    ®
    0.80
     ®
    0.80
     International
    0.80
    âĦ¢:
    0.79
     Society
    0.79
     Acad
    0.78
     Organization
    0.77
    Activations Density 0.177%

    No Known Activations