© 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 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. 0-RES-JB
    11. 13684
    Prev
    Next
    INDEX
    Explanations

    words related to educational institutions or certification programs

    oai_token-act-pair · gpt-3.5-turbo

    the acronym "OU" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smugglers
    -0.67
     mant
    -0.67
     Spice
    -0.62
     spice
    -0.60
     smugg
    -0.60
     crem
    -0.59
     Era
    -0.59
     neut
    -0.59
     recruitment
    -0.59
     Mith
    -0.58
    POSITIVE LOGITS
    OU
    4.17
    OUS
    1.96
    OUT
    1.70
    OUN
    1.57
    ou
    1.50
    OUR
    1.42
    OW
    1.41
    OVER
    1.37
    UD
    1.33
    OUGH
    1.31
    Activations Density 0.012%

    No Known Activations