© 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. 11-RES-JB
    11. 14215
    Prev
    Next
    INDEX
    Explanations

    specific dates or durations of time

    oai_token-act-pair · gpt-3.5-turbo

    temporal references and deadlines related to events or regulations

    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
     Ethiop
    -0.72
    ãĥĥãĥī
    -0.71
    jiang
    -0.70
    forts
    -0.68
    ãĥ³ãĤ¸
    -0.66
     metaphors
    -0.66
    ocus
    -0.66
    asca
    -0.65
    girls
    -0.65
    hots
    -0.65
    POSITIVE LOGITS
     expiration
    1.41
     receipt
    1.13
     date
    1.05
     issuance
    1.04
     deadline
    1.02
     calendar
    1.02
     January
    1.00
     commencement
    0.99
     termination
    0.99
     enactment
    0.98
    Activations Density 0.196%

    No Known Activations