© 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. 6776
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or people with the word "Wood" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Wood" and its variations 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
    ional
    -0.78
     disguise
    -0.69
    itia
    -0.68
    ysis
    -0.65
    oresc
    -0.65
    uates
    -0.64
     unres
    -0.64
     analges
    -0.61
    naires
    -0.61
     pand
    -0.61
    POSITIVE LOGITS
    ruff
    1.62
    stock
    1.20
    bridge
    1.19
    bury
    1.13
    working
    1.13
    row
    1.12
    lands
    1.06
    cutting
    1.06
    cock
    1.06
    fox
    1.05
    Activations Density 0.036%

    No Known Activations