© 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. 8-RES-JB
    11. 10216
    Prev
    Next
    INDEX
    Explanations

    keywords related to political extremism, including terms like "far-right" and "far-left"

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with political extremism, particularly 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Puzzles
    -0.76
     Solitaire
    -0.71
     McKenna
    -0.65
     Tid
    -0.64
     McH
    -0.64
     Sut
    -0.64
     Hyde
    -0.63
     PW
    -0.63
     Slug
    -0.62
     Scrib
    -0.62
    POSITIVE LOGITS
    reaching
    1.27
    ranging
    1.14
    fetched
    1.12
    sighted
    1.03
    astern
    0.90
    forward
    0.89
    away
    0.89
    east
    0.89
    road
    0.87
    bent
    0.87
    Activations Density 0.054%

    No Known Activations