© 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. 20325
    Prev
    Next
    INDEX
    Explanations

    specific instances where understanding or knowledge is explicitly mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "understands."

    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
    onies
    -0.86
    ads
    -0.74
     downed
    -0.73
    collection
    -0.72
    cial
    -0.67
    haps
    -0.65
    pmwiki
    -0.64
    ammy
    -0.63
    rav
    -0.63
    ogue
    -0.63
    POSITIVE LOGITS
     understands
    0.96
    ¿½
    0.89
     understood
    0.80
     Understand
    0.78
    ãĤ©
    0.78
     SERV
    0.77
    ledged
    0.73
    terday
    0.72
     Trident
    0.70
    uitive
    0.69
    Activations Density 0.003%

    No Known Activations