© 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. 1936
    Prev
    Next
    INDEX
    Explanations

    durations of time, specifically in days

    oai_token-act-pair · gpt-3.5-turbo

    references to specific durations of days

    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
    acus
    -0.78
    emale
    -0.75
    urities
    -0.75
    umbn
    -0.69
    versely
    -0.68
    rahim
    -0.67
    inav
    -0.65
    untled
    -0.64
    anooga
    -0.64
    ronics
    -0.64
    POSITIVE LOGITS
     ago
    1.00
    pring
    0.96
    dream
    0.95
    trip
    0.89
    care
    0.85
    hift
    0.78
    ilver
    0.76
    hops
    0.75
    days
    0.75
     apiece
    0.73
    Activations Density 0.047%

    No Known Activations