© 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. 11-RES-JB
    11. 22460
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a period of time or duration

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for a while" along with variations

    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
     helicop
    -0.68
     Soccer
    -0.63
    urated
    -0.61
    agonists
    -0.61
    acus
    -0.56
    rock
    -0.54
     bilingual
    -0.54
    Redd
    -0.52
     halftime
    -0.52
    roots
    -0.51
    POSITIVE LOGITS
     longer
    1.33
     ago
    1.08
     before
    0.82
     afterwards
    0.81
    cium
    0.77
     awhile
    0.76
     thereafter
    0.76
     afterward
    0.75
    OOK
    0.73
    til
    0.73
    Activations Density 0.081%

    No Known Activations