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

    Neuronpedia

    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. 20557
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'instant'

    oai_token-act-pair · gpt-3.5-turbo

    references to "instant" products or experiences

    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
    ALD
    -0.67
    umbing
    -0.67
    llah
    -0.66
     Spencer
    -0.61
    unin
    -0.59
    bands
    -0.59
    ramids
    -0.58
     Bureau
    -0.58
     Marketable
    -0.58
    ATHER
    -0.58
    POSITIVE LOGITS
    aneously
    2.02
    aneous
    1.64
     gratification
    1.52
    iation
    1.45
    iated
    1.45
    iations
    1.35
    iating
    1.31
    iate
    1.30
    iates
    1.16
     replay
    1.08
    Activations Density 0.039%

    No Known Activations