© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9942
    Prev
    Next
    INDEX
    Explanations

    words containing the letters "min"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific measurement or size denoted by the prefix "min."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Awakening
    -0.68
     reforming
    -0.67
     Danger
    -0.67
     Compass
    -0.65
    eering
    -0.61
     dove
    -0.61
    CLASSIFIED
    -0.60
     compe
    -0.57
    place
    -0.57
     FIRE
    -0.57
    POSITIVE LOGITS
    iatures
    1.45
    otaur
    1.30
    istries
    1.29
    nesota
    1.26
    usc
    1.23
    isite
    1.15
    ibus
    1.14
    ivan
    1.13
    istered
    1.13
    aret
    1.13
    Activations Density 0.015%

    No Known Activations