© 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. 6018
    Prev
    Next
    INDEX
    Explanations

    moments or instances

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moment" and expressions related to significant occurrences

    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
    ä¸Ĭ
    -0.66
    MIN
    -0.63
     princip
    -0.62
    GH
    -0.61
     Methods
    -0.60
     Plants
    -0.58
     Bones
    -0.57
    CAST
    -0.57
     PLAN
    -0.57
     TAMADRA
    -0.56
    POSITIVE LOGITS
    ary
    1.68
    ous
    1.67
    aries
    1.37
    ously
    1.32
    aneously
    1.12
    arily
    1.07
    icity
    1.04
    uality
    1.03
    ARY
    1.01
    icle
    0.99
    Activations Density 0.062%

    No Known Activations