© 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. 13166
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the source or origin of information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "from."

    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
    pled
    -0.70
    abeth
    -0.63
    tons
    -0.56
     consecut
    -0.56
     guarantee
    -0.55
    psey
    -0.55
    cum
    -0.54
    heres
    -0.54
    purpose
    -0.54
    stru
    -0.53
    POSITIVE LOGITS
     Flavoring
    0.85
     Subtle
    0.78
     TheNitromeFan
    0.76
     Wikimedia
    0.75
    pmwiki
    0.72
     Adinida
    0.71
     Encyclopedia
    0.71
     Pastebin
    0.71
     davidjl
    0.68
     Wow
    0.67
    Activations Density 0.031%

    No Known Activations