© 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. 7-RES-JB
    11. 3679
    Prev
    Next
    INDEX
    Explanations

    information related to legislation and regulations, as well as medical conditions like cramping or mood changes

    oai_token-act-pair · gpt-3.5-turbo

    concerns related to public health and legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonetheless
    -0.74
    ).[
    -0.65
     accordingly
    -0.62
    .''
    -0.62
    ?).
    -0.62
    ''.
    -0.61
     anyway
    -0.61
    ."[
    -0.60
     instead
    -0.58
     afterward
    -0.58
    POSITIVE LOGITS
    ournal
    0.59
    oug
    0.53
     FANTASY
    0.50
    earable
    0.49
     GD
    0.49
    irtual
    0.48
    urrency
    0.48
     Albion
    0.47
    yrights
    0.47
    cohol
    0.46
    Activations Density 1.664%

    No Known Activations