© 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. 2-RES-JB
    11. 463
    Prev
    Next
    INDEX
    Explanations

    the word or word segment "oles"

    oai_token-act-pair · gpt-4-turbo

    words related to holes or cavities

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of a particular name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reply
    -0.68
    è¦ļéĨĴ
    -0.65
    Flight
    -0.65
    ãģ®å®
    -0.63
    ANC
    -0.62
    EXP
    -0.61
     Chronicle
    -0.61
    ãĥ©ãĥ³
    -0.59
     Judgment
    -0.58
     EDITION
    -0.57
    POSITIVE LOGITS
    oles
    1.43
    ole
    0.99
    pora
    0.94
    ols
    0.92
    terness
    0.89
    ummer
    0.87
    hift
    0.87
    hene
    0.86
    ophy
    0.84
    ippi
    0.83
    Activations Density 0.003%

    No Known Activations