© 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. 20883
    Prev
    Next
    INDEX
    Explanations

    nationalities or religious affiliations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with political and ethnic identities

    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
    ravings
    -1.01
    ories
    -1.00
    isites
    -0.98
    atories
    -0.97
    onies
    -0.97
    boards
    -0.96
    ologies
    -0.94
    bows
    -0.94
    encies
    -0.94
    brids
    -0.92
    POSITIVE LOGITS
     politician
    1.28
     thinker
    1.28
     journalist
    1.20
     who
    1.19
     citizen
    1.18
     traveler
    1.17
     businessman
    1.16
     legislator
    1.15
     diplomat
    1.13
     woman
    1.12
    Activations Density 0.253%

    No Known Activations