© 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. 10-RES-JB
    11. 20199
    Prev
    Next
    INDEX
    Explanations

    phrases related to the capacity or max number of people or things that something can accommodate

    oai_token-act-pair · gpt-3.5-turbo

    quantitative information regarding capacity or sizes of groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pse
    -0.78
    saf
    -0.71
     à¨
    -0.69
    uture
    -0.64
     disapp
    -0.64
     coincidence
    -0.63
     obscurity
    -0.63
     mockery
    -0.63
     retribution
    -0.62
    rade
    -0.62
    POSITIVE LOGITS
     guests
    1.24
     occupants
    1.21
     passengers
    1.14
     servings
    0.95
     beds
    0.94
     spectators
    0.94
     occupant
    0.93
     adults
    0.93
     Guests
    0.93
     patrons
    0.92
    Activations Density 0.289%

    No Known Activations