© 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. 14505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast/consequences

    oai_token-act-pair · gpt-3.5-turbo

    em dashes and phrases that connect ideas or indicate ongoing thoughts

    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
     obser
    -0.84
     lifes
    -0.77
     sleeper
    -0.77
     subsequ
    -0.73
     cons
    -0.73
    omorphic
    -0.72
    ccording
    -0.72
    itton
    -0.71
    ĵĺ
    -0.71
     stabil
    -0.70
    POSITIVE LOGITS
    ––
    0.87
     ---
    0.85
    _-
    0.84
    [[
    0.81
    ————
    0.81
     WATCHED
    0.81
     Cosponsors
    0.81
    âĸº
    0.80
     âĢķ
    0.80
    SEE
    0.79
    Activations Density 0.031%

    No Known Activations