© 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. 12-RES-JB
    11. 4060
    Prev
    Next
    INDEX
    Explanations

    titles or honorifics used before a person's name

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of individuals with the title "Sir."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     prelim
    -0.71
     darker
    -0.70
     sparse
    -0.68
     cycle
    -0.68
     open
    -0.66
     duplicate
    -0.66
     similar
    -0.66
     lackluster
    -0.65
     expend
    -0.65
     developed
    -0.64
    POSITIVE LOGITS
    zech
    1.08
    aj
    0.98
    dinand
    0.98
    leaf
    0.98
    aldo
    0.95
    ius
    0.95
    han
    0.94
     Gaw
    0.92
     Edmund
    0.91
     Malcolm
    0.90
    Activations Density 0.012%

    No Known Activations