© 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. 6835
    Prev
    Next
    INDEX
    Explanations

    references to materials made of specific substances

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of polymers, particularly those that begin with "poly."

    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
     Jaw
    -0.65
     trove
    -0.64
     Burnett
    -0.63
     onset
    -0.63
     inflicting
    -0.62
     Eternity
    -0.60
     documenting
    -0.60
     dehuman
    -0.60
     CARE
    -0.59
     centre
    -0.58
    POSITIVE LOGITS
    gon
    1.43
    mers
    1.35
    ester
    1.32
    phony
    1.32
    meric
    1.29
    chrome
    1.21
    phen
    1.19
    ethyl
    1.17
    sac
    1.16
    morph
    1.16
    Activations Density 0.024%

    No Known Activations