© 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. 10-RES-JB
    11. 8297
    Prev
    Next
    INDEX
    Explanations

    words related to containers used for carrying or holding items, such as "bucket" and "basket."

    oai_token-act-pair · gpt-3.5-turbo

    references to containers, specifically buckets and baskets

    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
    uality
    -0.83
    士
    -0.81
    entious
    -0.70
    uton
    -0.68
     resid
    -0.65
    encing
    -0.65
    utenant
    -0.63
    encer
    -0.62
    inct
    -0.62
    inel
    -0.62
    POSITIVE LOGITS
    jee
    0.98
    pillar
    0.88
    ware
    0.84
    rella
    0.79
    istical
    0.78
    combe
    0.77
    halla
    0.77
    chell
    0.77
    heit
    0.76
    ique
    0.75
    Activations Density 0.116%

    No Known Activations