© 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. 9-RES-JB
    11. 7470
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and economic policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taxation and public policy reforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.76
    semble
    -0.73
    cific
    -0.70
     manoeuv
    -0.70
     partName
    -0.69
     ensemble
    -0.67
     whim
    -0.66
     Frie
    -0.66
    worthiness
    -0.66
    hooting
    -0.65
    POSITIVE LOGITS
    amacare
    1.30
     Medicare
    1.16
     Obamacare
    1.11
     ObamaCare
    1.10
     taxes
    1.00
     Voting
    1.00
     amnesty
    0.97
     Affordable
    0.96
     Medicaid
    0.95
     tuition
    0.93
    Activations Density 0.677%

    No Known Activations