© 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. 8-RES-JB
    11. 3350
    Prev
    Next
    INDEX
    Explanations

    economic and political terms

    oai_token-act-pair · gpt-3.5-turbo

    references to economic and political entities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Soph
    -0.63
    estern
    -0.58
     sle
    -0.58
    yip
    -0.56
    ukong
    -0.55
     wonders
    -0.54
    GW
    -0.54
     millenn
    -0.54
    atcher
    -0.53
     Wra
    -0.53
    POSITIVE LOGITS
    .''.
    0.99
     lest
    0.98
    '.
    0.97
     thereby
    0.93
    $.
    0.92
     instead
    0.91
    *.
    0.89
    .[
    0.89
     rather
    0.88
    .).
    0.84
    Activations Density 1.001%

    No Known Activations