© 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. 11979
    Prev
    Next
    INDEX
    Explanations

    patterns related to grammar and language structure, such as identifying participles, verbs, and genitive forms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to grammar and language structure

    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
     Jericho
    -0.84
     Avalon
    -0.83
     WiFi
    -0.81
     Goddard
    -0.79
     Sunshine
    -0.78
     Niagara
    -0.76
     Roberts
    -0.76
     Hobby
    -0.75
     Pinball
    -0.75
     WWF
    -0.74
    POSITIVE LOGITS
     verbs
    1.86
     noun
    1.76
     pronouns
    1.64
     vowel
    1.63
     pronoun
    1.60
     adject
    1.58
     verb
    1.57
     conson
    1.48
     syll
    1.45
     adjective
    1.43
    Activations Density 0.344%

    No Known Activations