© 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. 11-RES-JB
    11. 21035
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to policies, reports, and social issues

    oai_token-act-pair · gpt-3.5-turbo

    indicators of social issues affecting marginalized groups

    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
     Catalyst
    -0.73
     Babel
    -0.73
     warp
    -0.70
     Zeit
    -0.68
     Tulsa
    -0.68
     Strawberry
    -0.68
     Rez
    -0.67
     CLR
    -0.67
     Rhodes
    -0.66
     antic
    -0.65
    POSITIVE LOGITS
    who
    1.52
    selves
    1.28
    whose
    1.09
    their
    1.02
    owners
    1.00
    living
    0.97
     who
    0.94
     whom
    0.94
    elected
    0.93
    ï¸ı
    0.92
    Activations Density 0.296%

    No Known Activations