© 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. 10-RES-JB
    11. 18912
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating anticipation or potential outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "stands to," indicating potentiality or obligation

    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
    quickShipAvailable
    -0.81
    é¾įåĸļ士
    -0.67
    breaks
    -0.63
     Going
    -0.62
     Blaze
    -0.62
    going
    -0.62
     Tempest
    -0.60
    heres
    -0.58
    standing
    -0.57
    etheless
    -0.56
    POSITIVE LOGITS
     inherit
    1.01
     gain
    1.01
     lose
    1.00
     benefit
    0.97
     capitalize
    0.93
     receive
    0.89
     reap
    0.88
    asted
    0.85
     learn
    0.85
    -----------
    0.83
    Activations Density 0.037%

    No Known Activations