© 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. 1-RES-JB
    11. 543
    Prev
    Next
    INDEX
    Explanations

    the phrase "Live in the moment."

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boo
    -0.74
    luaj
    -0.70
    TPPStreamerBot
    -0.61
    rontal
    -0.59
     Forever
    -0.57
     Workers
    -0.57
    hood
    -0.57
     holiest
    -0.56
     tert
    -0.54
     Future
    -0.54
    POSITIVE LOGITS
    igators
    0.78
    igator
    0.76
    ented
    0.74
    Ott
    0.74
    arettes
    0.73
    gart
    0.72
    oeuv
    0.71
     "$:/
    0.69
    orio
    0.69
    zbollah
    0.68
    Activations Density 0.000%

    No Known Activations