© 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. 8-RES-JB
    11. 22321
    Prev
    Next
    INDEX
    Explanations

    words related to libraries

    oai_token-act-pair · gpt-3.5-turbo

    references to libraries and their various roles or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samoa
    -0.67
    lers
    -0.65
    assis
    -0.62
    natal
    -0.61
    imer
    -0.61
    uler
    -0.61
    ibal
    -0.60
    engeance
    -0.60
    Pacific
    -0.59
    ilon
    -0.58
    POSITIVE LOGITS
    ibrarian
    0.89
     shelves
    0.86
    pedia
    0.75
    ãĥ´ãĤ¡
    0.74
    mage
    0.74
    artment
    0.73
     dumps
    0.72
    ibraries
    0.71
    ibrary
    0.71
    sonian
    0.70
    Activations Density 0.036%

    No Known Activations