© 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. 12304
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news sources

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations, media outlets, and possibly photography credits

    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
     Paran
    -0.87
     agre
    -0.82
     Bean
    -0.71
     metic
    -0.70
     unnecess
    -0.69
     Aval
    -0.69
     belts
    -0.68
     oun
    -0.68
     paran
    -0.67
     Ich
    -0.67
    POSITIVE LOGITS
    soDeliveryDate
    1.10
    Brend
    0.91
    rill
    0.83
    iller
    0.81
    ILL
    0.79
    iffin
    0.75
    dll
    0.74
    047
    0.74
    050
    0.73
    ler
    0.73
    Activations Density 0.280%

    No Known Activations