© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20737
    Prev
    Next
    INDEX
    Explanations

    proper nouns or technical terms related to human biology or medicine

    oai_token-act-pair · gpt-3.5-turbo

    references to kin and related terminology

    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
    enance
    -0.97
     Mellon
    -0.80
     Seym
    -0.72
     Merry
    -0.64
    ORD
    -0.62
     fine
    -0.62
    worthiness
    -0.61
     Ronaldo
    -0.60
    channelAvailability
    -0.60
     Penet
    -0.59
    POSITIVE LOGITS
    etic
    1.53
    etics
    1.50
    etically
    1.32
    folk
    1.14
    esthetic
    1.12
    zie
    1.07
    sey
    1.06
    ney
    1.05
    ners
    1.02
    ja
    1.02
    Activations Density 0.065%

    No Known Activations