© 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. 6-RES-JB
    11. 11764
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "here we go."

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around shared experiences and continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tm
    -0.70
    advertising
    -0.70
     tamp
    -0.69
     Favorite
    -0.65
    ongo
    -0.63
    iatric
    -0.61
     nickname
    -0.61
     Amen
    -0.60
     Advertisement
    -0.59
    /#
    -0.59
    POSITIVE LOGITS
    itia
    0.69
     Spiel
    0.66
    RAW
    0.65
    rot
    0.64
    hung
    0.63
    rower
    0.62
    ÃįÃį
    0.61
     ripe
    0.60
    erers
    0.60
    asion
    0.59
    Activations Density 0.109%

    No Known Activations