© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5516
    Prev
    Next
    INDEX
    Explanations

    words related to clicking or interactions with digital content

    oai_token-act-pair · gpt-3.5-turbo

    references to actions involving clicking, particularly in the context of online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zona
    -0.72
    adium
    -0.66
     coun
    -0.62
     alle
    -0.61
     Variety
    -0.60
     Scotia
    -0.59
     Ness
    -0.59
    utive
    -0.58
    ZA
    -0.57
     Catalonia
    -0.57
    POSITIVE LOGITS
    through
    0.89
    lish
    0.86
    iard
    0.80
    prints
    0.80
    ety
    0.79
    wheel
    0.78
     clicks
    0.77
    zag
    0.75
    oola
    0.74
    dress
    0.73
    Activations Density 0.036%

    No Known Activations