© 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. 9-RES-JB
    11. 10409
    Prev
    Next
    INDEX
    Explanations

    descriptions of spaces and their capacity in terms of people

    oai_token-act-pair · gpt-3.5-turbo

    references to the capacity or number of people an area or facility can accommodate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regrets
    -0.66
    gotten
    -0.63
     Genocide
    -0.63
    IELD
    -0.62
    IRD
    -0.58
    versive
    -0.58
    inventoryQuantity
    -0.57
    rog
    -0.56
    bara
    -0.56
     fears
    -0.56
    POSITIVE LOGITS
     apiece
    1.61
     totaling
    1.18
     crammed
    1.07
     each
    1.05
     spaced
    0.99
     consisting
    0.99
     ranging
    0.98
     depending
    0.98
     plus
    0.96
    each
    0.95
    Activations Density 0.390%

    No Known Activations