© 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. 3-RES-JB
    11. 596
    Prev
    Next
    INDEX
    Explanations

    physical objects or concepts related to various fields and domains

    oai_token-act-pair · gpt-3.5-turbo

    nouns and specific objects related to various contexts and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berra
    -0.61
    NetMessage
    -0.60
     Flavoring
    -0.60
    laus
    -0.56
    Redd
    -0.54
     Magicka
    -0.53
     Residential
    -0.53
    vironment
    -0.51
    llular
    -0.50
    lihood
    -0.50
    POSITIVE LOGITS
     cutter
    0.68
    wright
    0.63
    washer
    0.62
    wife
    0.61
    folio
    0.61
     regiment
    0.61
    fighter
    0.61
    maker
    0.60
     rul
    0.60
     maker
    0.60
    Activations Density 0.748%

    No Known Activations