© 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. 21205
    Prev
    Next
    INDEX
    Explanations

    numbers, URLs, and email addresses in text

    oai_token-act-pair · gpt-3.5-turbo

    characters, symbols, and formats associated with URLs and online content

    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
     Coul
    -0.89
     Schultz
    -0.86
     Bulgar
    -0.85
    kel
    -0.84
     Jenna
    -0.83
    729
    -0.81
     Nun
    -0.81
     Bun
    -0.81
     Clover
    -0.80
     Kemp
    -0.79
    POSITIVE LOGITS
    ardi
    1.07
    ARD
    0.93
    ard
    0.91
    ĩ
    0.89
    ords
    0.88
    ARDS
    0.86
     Jord
    0.84
    ARI
    0.83
     Rom
    0.83
    ART
    0.81
    Activations Density 0.695%

    No Known Activations