© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2794
    Prev
    Next
    INDEX
    Explanations

    phrases related to extreme political ideologies or movements, particularly those on the far-right

    oai_token-act-pair · gpt-3.5-turbo

    mention of far-left and far-right political ideologies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sugar
    -0.75
     Phi
    -0.71
     Scrib
    -0.68
     Peel
    -0.65
     Creator
    -0.65
     McH
    -0.65
     Solitaire
    -0.65
     Puzzles
    -0.65
     authentication
    -0.64
     Sut
    -0.62
    POSITIVE LOGITS
    reaching
    1.47
    ranging
    1.35
    fetched
    1.35
    sighted
    1.28
    fl
    1.20
    away
    1.12
    haired
    1.12
    east
    1.12
    eyed
    1.11
    distance
    1.10
    Activations Density 0.015%

    No Known Activations