© 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. 1-RES-JB
    11. 3451
    Prev
    Next
    INDEX
    Explanations

    grammatical elements, specifically nouns, adjectives, pronouns, and verbs

    oai_token-act-pair · gpt-3.5-turbo

    references to parts of speech, particularly nouns and adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersen
    -0.73
    rared
    -0.73
    cler
    -0.72
    utherland
    -0.69
    ONSORED
    -0.69
     Nelson
    -0.66
    imilar
    -0.65
    psey
    -0.65
     Rider
    -0.65
    clerosis
    -0.65
    POSITIVE LOGITS
     noun
    1.03
     adjective
    0.96
    ciation
    0.96
     pronouns
    0.96
    matical
    0.92
     suffix
    0.90
     adject
    0.90
     phrase
    0.86
     verbs
    0.85
     pronoun
    0.83
    Activations Density 0.015%

    No Known Activations