© 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. 9478
    Prev
    Next
    INDEX
    Explanations

    expressions indicating quotes or statements being made by someone

    oai_token-act-pair · gpt-3.5-turbo

    statements that indicate someone is quoting or attributing information

    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
    iership
    -0.73
    ',
    -0.71
    ait
    -0.64
    ,'
    -0.63
    execute
    -0.63
    die
    -0.62
    tumblr
    -0.61
    unker
    -0.61
    ective
    -0.60
    align
    -0.60
    POSITIVE LOGITS
     adding
    0.86
     quoting
    0.82
     emphasis
    0.81
     elabor
    0.81
     understatement
    0.80
     nods
    0.79
     sarcast
    0.77
     paraph
    0.75
     rhet
    0.75
     pauses
    0.75
    Activations Density 0.182%

    No Known Activations