© 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. 3805
    Prev
    Next
    INDEX
    Explanations

    terms related to discussing or addressing societal or political issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social issues and consumer concerns

    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
     coerced
    -0.79
    Beta
    -0.76
    Tes
    -0.70
     Rober
    -0.70
     Firm
    -0.69
    emade
    -0.69
     Vers
    -0.69
    atan
    -0.68
     Royale
    -0.66
     sorcerer
    -0.65
    POSITIVE LOGITS
     focus
    1.37
    focus
    1.29
     concern
    1.23
     focuses
    1.19
     topics
    1.14
     cares
    1.13
     discussion
    1.13
     focused
    1.12
     attention
    1.11
     foc
    1.09
    Activations Density 0.558%

    No Known Activations