© 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. 12-RES-JB
    11. 2784
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limitation or restriction

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    PDATE
    -0.73
     Mandatory
    -0.73
     Roz
    -0.71
     Quarter
    -0.68
     Tradition
    -0.67
     Canary
    -0.66
     millenn
    -0.65
     Seym
    -0.64
     mosqu
    -0.64
     Surveillance
    -0.63
    POSITIVE LOGITS
    't
    1.53
     hardly
    1.11
    NOT
    1.08
     scarcely
    1.05
     easily
    1.03
     only
    0.97
     never
    0.96
    adian
    0.95
    isters
    0.94
     plaus
    0.93
    Activations Density 0.119%

    No Known Activations