© 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. 11-RES-JB
    11. 8310
    Prev
    Next
    INDEX
    Explanations

    specific mention of the term "Mo" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mo" or words starting with "Mo."

    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
     responsibility
    -0.66
    âĢ¢âĢ¢
    -0.63
     polarized
    -0.62
     DRAGON
    -0.60
     Hurricanes
    -0.59
    nai
    -0.58
    upon
    -0.55
     pret
    -0.54
     Integrity
    -0.54
     occasion
    -0.54
    POSITIVE LOGITS
    aning
    1.12
    ogle
    1.10
    aned
    1.10
    orthy
    1.05
    jo
    1.05
    ose
    1.03
    ogly
    1.03
    oney
    1.02
    eller
    1.01
    zilla
    0.95
    Activations Density 0.044%

    No Known Activations