© 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. 11-RES-JB
    11. 17479
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific location (Burnham)`

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Burn" in various contexts

    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
    kson
    -0.64
     Finnish
    -0.63
     TODAY
    -0.62
     Croatian
    -0.58
     Allaah
    -0.57
     penn
    -0.57
     OWN
    -0.57
     Emir
    -0.56
     NETWORK
    -0.56
     Nex
    -0.56
    POSITIVE LOGITS
    aby
    1.16
    ished
    1.09
    lett
    1.08
    emouth
    1.00
    side
    0.95
    er
    0.95
    itzer
    0.92
    leys
    0.90
    ley
    0.90
    ishing
    0.88
    Activations Density 0.076%

    No Known Activations