© 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. 11990
    Prev
    Next
    INDEX
    Explanations

    specific time-related expressions or mentions of days of the week

    oai_token-act-pair · gpt-3.5-turbo

    temporal references related to events and statements

    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
    pires
    -0.71
    =-=-=-=-=-=-=-=-
    -0.56
    ////////////////////////////////
    -0.56
     beware
    -0.55
    CLASSIFIED
    -0.55
    UGE
    -0.54
    guyen
    -0.54
     xp
    -0.53
     saves
    -0.53
     havoc
    -0.53
    POSITIVE LOGITS
     praising
    1.03
     criticizing
    1.02
     recount
    1.00
     regarding
    0.99
     stating
    0.99
     outlining
    0.98
     saying
    0.97
     detailing
    0.96
     announcing
    0.96
     alleging
    0.95
    Activations Density 0.213%

    No Known Activations