© 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. 2046
    Prev
    Next
    INDEX
    Explanations

    words related to library and librarians

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "library" along with related terms and concepts

    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
     mitigation
    -0.75
    chal
    -0.70
    erness
    -0.67
     conversion
    -0.66
    Ĥ¬
    -0.64
    pper
    -0.64
    meal
    -0.63
    WARD
    -0.63
    than
    -0.62
    peak
    -0.62
    POSITIVE LOGITS
    illation
    1.05
    arians
    1.04
    antes
    1.01
    acies
    0.96
    itation
    0.95
    itating
    0.95
    ancies
    0.93
    itated
    0.92
    antly
    0.90
    aceutical
    0.90
    Activations Density 0.055%

    No Known Activations