© 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. 17737
    Prev
    Next
    INDEX
    Explanations

    sentences that end with emphatic punctuation and suggest a strong statement or action

    oai_token-act-pair · gpt-3.5-turbo

    statements of personal experiences or feelings

    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
     compr
    -0.81
     respectively
    -0.73
     inver
    -0.73
     arrang
    -0.72
     proport
    -0.72
     challeng
    -0.71
     charact
    -0.71
    uler
    -0.71
     necess
    -0.70
    inement
    -0.70
    POSITIVE LOGITS
     Literally
    1.31
     Lots
    1.17
     Absolutely
    1.05
     Period
    1.04
     Seriously
    1.01
     Probably
    0.98
     Twice
    0.96
     Kills
    0.96
     Didn
    0.96
     Everybody
    0.96
    Activations Density 0.535%

    No Known Activations