© 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. 3-RES-JB
    11. 16499
    Prev
    Next
    INDEX
    Explanations

    the word "Bis" or variations of it, like "Biswanath" or "Bisque"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.90
    âĶģ
    -0.79
    ively
    -0.78
    bies
    -0.76
    INGS
    -0.71
    iveness
    -0.71
    */(
    -0.70
    BOOK
    -0.67
    isters
    -0.67
    Agent
    -0.65
    POSITIVE LOGITS
    ection
    0.93
    incarn
    0.86
    ected
    0.83
    ector
    0.82
     bis
    0.80
    cel
    0.78
    sel
    0.76
    pend
    0.76
    sei
    0.75
    acha
    0.70
    Activations Density 0.014%

    No Known Activations