© 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. 20645
    Prev
    Next
    INDEX
    Explanations

    mentions of locations in political contexts, specifically the term "far" in a political or geographic connotation

    oai_token-act-pair · gpt-3.5-turbo

    references to political extremes, particularly related to the "far" left and "far" right

    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
     Slug
    -0.62
     PID
    -0.62
     Rankings
    -0.61
     Ortiz
    -0.60
     Polo
    -0.60
     Mechanics
    -0.57
     Peel
    -0.57
     Maver
    -0.56
     Amos
    -0.56
     Surgery
    -0.56
    POSITIVE LOGITS
    away
    1.19
     flung
    1.18
    aday
    1.07
    med
    1.04
    fetched
    1.02
    riers
    1.00
    ce
    0.99
    thing
    0.97
    seeing
    0.94
    rowing
    0.94
    Activations Density 0.026%

    No Known Activations