© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1571
    Prev
    Next
    INDEX
    Explanations

    references to collections, such as "expensive collection of pornographic movies," "lining up for the collection," "collection of skulls," and "collection of belief, assumptions, memories."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "collection" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.70
    sey
    -0.68
    pher
    -0.68
     Orth
    -0.66
    yl
    -0.64
    IELD
    -0.62
    ा
    -0.61
     Centauri
    -0.61
    mers
    -0.60
    MER
    -0.60
    POSITIVE LOGITS
    ibles
    0.86
     collector
    0.82
    icles
    0.81
    ivist
    0.81
    sonian
    0.80
    asso
    0.80
    ivities
    0.78
    govtrack
    0.78
    uably
    0.77
    ennial
    0.77
    Activations Density 0.073%

    No Known Activations