© 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. 9-RES-JB
    11. 11149
    Prev
    Next
    INDEX
    Explanations

    words related to exercising authority or control over something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to imposition or enforcement of rules, regulations, and taxes

    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
    gnu
    -0.81
    wagen
    -0.75
    DragonMagazine
    -0.74
    abet
    -0.74
    rous
    -0.73
    rich
    -0.73
    api
    -0.73
    vironment
    -0.71
    tes
    -0.71
    ansas
    -0.71
    POSITIVE LOGITS
     stricter
    1.04
     restrictions
    1.03
     sanctions
    1.03
     harsher
    1.01
     punishments
    0.98
     tariffs
    0.95
     burdens
    0.93
     restraints
    0.93
     penalties
    0.91
     limits
    0.90
    Activations Density 0.081%

    No Known Activations