© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9104
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "just in time" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.77
    only
    -0.75
    dominated
    -0.72
    chwitz
    -0.67
    pora
    -0.64
     only
    -0.63
    anon
    -0.63
    rahim
    -0.63
    bender
    -0.63
    abis
    -0.62
    POSITIVE LOGITS
     luck
    0.75
     mention
    0.75
     nick
    0.71
     coincidence
    0.69
     whiff
    0.68
     glimpse
    0.67
     curiosity
    0.67
    angles
    0.65
     glimps
    0.65
     case
    0.64
    Activations Density 0.079%

    No Known Activations