© 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. 1-RES-JB
    11. 10349
    Prev
    Next
    INDEX
    Explanations

    words with diacritics

    oai_token-act-pair · gpt-3.5-turbo

    French words that begin with the letter "é"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blazers
    -0.77
     Lovecraft
    -0.73
    enged
    -0.71
    itude
    -0.71
    utterstock
    -0.71
     DPR
    -0.70
     Painter
    -0.68
     Plum
    -0.67
     Chattanooga
    -0.66
    hess
    -0.65
    POSITIVE LOGITS
     é
    1.32
    ÃįÃį
    1.09
     Ãī
    1.08
    lé
    1.07
    sembly
    1.01
    Ãī
    0.91
    izoph
    0.90
    rique
    0.86
    én
    0.86
     corrid
    0.84
    Activations Density 0.007%

    No Known Activations