© 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. 11-RES-JB
    11. 14627
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to planning or preparation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to planning and organization of activities or events

    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
    govtrack
    -0.79
    lished
    -0.76
    avery
    -0.72
    brand
    -0.70
    ĪĴ
    -0.70
    bery
    -0.69
    inth
    -0.69
    atsu
    -0.68
    ensional
    -0.67
    insured
    -0.66
    POSITIVE LOGITS
     ahead
    1.18
     trips
    1.07
     vacations
    1.06
     accordingly
    1.05
     beforehand
    0.96
     meals
    0.92
     obs
    0.90
     weddings
    0.88
     routes
    0.87
     meetings
    0.85
    Activations Density 0.121%

    No Known Activations