© 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. 1515
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to businesses or entities with "Gre" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to "Grease" or elements associated with it

    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
     Tonight
    -0.58
     istg
    -0.58
     Oath
    -0.57
     innocence
    -0.57
    Fram
    -0.56
     laps
    -0.55
     messenger
    -0.54
    ional
    -0.54
     Reward
    -0.53
     Mirror
    -0.53
    POSITIVE LOGITS
    enery
    1.37
    ysc
    1.25
    aves
    1.19
    edy
    1.15
    asers
    1.09
    yson
    1.09
    xit
    1.09
    asy
    1.08
    ased
    1.03
    gg
    1.01
    Activations Density 0.031%

    No Known Activations