© 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. 1479
    Prev
    Next
    INDEX
    Explanations

    the word "ham" combined with a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Birmingham" or related geographical terms

    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
    uary
    -0.73
    atively
    -0.65
    ELF
    -0.64
    Æ
    -0.63
    ahead
    -0.62
    cius
    -0.62
    REDACTED
    -0.57
    VO
    -0.57
    PLAY
    -0.56
    inventoryQuantity
    -0.56
    POSITIVE LOGITS
    pton
    1.81
    mers
    1.30
    ilton
    1.27
    sburg
    1.17
    monds
    1.17
    enei
    1.14
    shire
    1.12
    sted
    1.10
    MER
    1.07
    med
    1.04
    Activations Density 0.051%

    No Known Activations