© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2641
    Prev
    Next
    INDEX
    Explanations

    words related to switches or actions involving switches

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "switch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    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

    Negative Logits
    za
    -0.69
     oun
    -0.68
    apolis
    -0.67
    ICAN
    -0.65
    vez
    -0.63
    1981
    -0.61
    naire
    -0.60
     Mehran
    -0.60
    vae
    -0.59
    kamp
    -0.59
    POSITIVE LOGITS
    blade
    1.17
    grass
    1.11
    gear
    1.05
    backs
    1.00
    aroo
    0.87
    switch
    0.87
     switch
    0.86
    over
    0.82
    back
    0.82
     switches
    0.80
    Activations Density 0.030%

    No Known Activations