© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 2725
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and durations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating time duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    groups
    -0.91
    irtual
    -0.84
    ierrez
    -0.82
    coins
    -0.78
    ãĤ¨ãĥ«
    -0.77
    cases
    -0.77
    zee
    -0.75
    Tags
    -0.73
    agonists
    -0.73
    affles
    -0.73
    POSITIVE LOGITS
     year
    1.49
     decade
    1.47
     month
    1.43
     hour
    1.40
     week
    1.38
     semester
    1.36
     day
    1.31
     season
    1.30
     century
    1.25
     lifetime
    1.23
    Activations Density 0.200%

    No Known Activations