© 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. 10-RES-JB
    11. 7057
    Prev
    Next
    INDEX
    Explanations

    statements expressing support or favor for certain proposals or positions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of support or opposition to policies and legislation

    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
    istical
    -0.82
    abulary
    -0.80
    DragonMagazine
    -0.75
    zie
    -0.73
    ixtape
    -0.71
    æ©Ł
    -0.70
    wig
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    iquette
    -0.69
    krit
    -0.68
    POSITIVE LOGITS
     legalizing
    1.24
     abol
    1.18
     repealing
    1.17
     banning
    1.09
     allowing
    1.08
     extending
    1.06
     eliminating
    1.06
     arming
    1.05
     adopting
    1.04
     decriminal
    1.02
    Activations Density 0.156%

    No Known Activations