© 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. 3788
    Prev
    Next
    INDEX
    Explanations

    words that are closely related or interchangeable with each other, often used as synonyms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to concepts of being synonymous or equivalent

    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
    annis
    -0.69
    izons
    -0.63
    vae
    -0.63
     Psychology
    -0.63
     restraining
    -0.61
    ihad
    -0.61
    doors
    -0.59
     Dalai
    -0.59
    UGE
    -0.59
    uld
    -0.58
    POSITIVE LOGITS
     synonymous
    1.41
    ophon
    0.80
    iso
    0.78
    ansk
    0.77
     symbol
    0.74
    opolis
    0.74
     Nadu
    0.73
    akis
    0.72
     additive
    0.71
    onymous
    0.71
    Activations Density 0.013%

    No Known Activations