© 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. 11553
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Roger

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Roger."

    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
    runtime
    -0.66
    ahime
    -0.64
    igure
    -0.63
     sisters
    -0.60
    marked
    -0.57
    amaz
    -0.57
     civ
    -0.57
    itect
    -0.56
    isf
    -0.55
     upkeep
    -0.55
    POSITIVE LOGITS
     Goodell
    1.06
     Waters
    0.99
     Rabbit
    0.89
     Stone
    0.86
     Zel
    0.86
     Godd
    0.82
     Bacon
    0.80
     Ding
    0.80
     Revel
    0.78
     Chaff
    0.76
    Activations Density 0.035%

    No Known Activations