© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1989
    Prev
    Next
    INDEX
    Explanations

    symbols related to text formatting or emojis

    oai_token-act-pair · gpt-3.5-turbo

    elements represented by the special characters and their associated contexts

    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
     guiName
    -0.79
     ACTIONS
    -0.73
     Solitaire
    -0.69
     seiz
    -0.65
     Shroud
    -0.63
     Bench
    -0.63
     Skydragon
    -0.62
     Farming
    -0.62
     scattering
    -0.61
     Pavilion
    -0.61
    POSITIVE LOGITS
    *)
    1.37
    >)
    1.33
    .).
    1.29
    !).
    1.24
    ).
    1.22
    ?).
    1.22
    !)
    1.20
    ?)
    1.16
    )."
    1.16
    )-
    1.16
    Activations Density 0.049%

    No Known Activations