© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 5922
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a duration of time

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for a while."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    origin
    -0.67
    eus
    -0.66
    anic
    -0.66
    emort
    -0.65
     Soccer
    -0.60
    opoly
    -0.59
    iquette
    -0.59
     reconc
    -0.59
    cham
    -0.58
    acus
    -0.57
    POSITIVE LOGITS
     ago
    0.93
     longer
    0.90
    OOK
    0.78
     Ago
    0.70
    cium
    0.67
     overdue
    0.65
     Leban
    0.63
    mma
    0.63
     sidx
    0.62
    maxwell
    0.62
    Activations Density 0.039%

    No Known Activations