© 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. 11-RES-JB
    11. 2434
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences addressing various social, political, or moral issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to significant societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    Laughs
    -0.86
    NES
    -0.78
    OGR
    -0.78
    avid
    -0.70
    ords
    -0.68
    aughs
    -0.68
    quite
    -0.67
    keys
    -0.67
    COMPLE
    -0.67
    Act
    -0.66
    POSITIVE LOGITS
     whether
    1.33
     how
    1.10
     fairness
    1.08
     legality
    1.07
     why
    1.05
     accountability
    1.03
     eligibility
    1.03
     affordability
    0.97
     transparency
    0.97
     privacy
    0.95
    Activations Density 0.223%

    No Known Activations