© 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. 3507
    Prev
    Next
    INDEX
    Explanations

    terms related to extreme political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to extreme political ideologies

    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
     Scrib
    -0.78
     attraction
    -0.67
     Doodle
    -0.66
     pumps
    -0.66
     Sugar
    -0.66
     submission
    -0.66
     metadata
    -0.65
     couple
    -0.65
     Parenthood
    -0.64
     McH
    -0.64
    POSITIVE LOGITS
    reaching
    1.70
    fetched
    1.69
    sighted
    1.64
    ranging
    1.49
    fl
    1.43
    seeing
    1.42
    left
    1.39
    right
    1.33
    too
    1.30
    away
    1.24
    Activations Density 0.018%

    No Known Activations