© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18731
    Prev
    Next
    INDEX
    Explanations

    words related to societal, political, and environmental issues

    oai_token-act-pair · gpt-3.5-turbo

    themes related to societal issues and artistic expression

    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
    ificantly
    -0.82
    orthy
    -0.77
    illy
    -0.76
    inion
    -0.70
    ivably
    -0.70
    ificant
    -0.69
    stantial
    -0.68
    MpServer
    -0.66
    biased
    -0.66
    verified
    -0.65
    POSITIVE LOGITS
     plag
    0.88
     of
    0.87
     afforded
    0.86
     lurking
    0.84
     unleashed
    0.80
     emanating
    0.79
     surrounding
    0.78
     engulf
    0.77
     endured
    0.76
     championed
    0.74
    Activations Density 0.580%

    No Known Activations