© 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. 2-RES-JB
    11. 18765
    Prev
    Next
    INDEX
    Explanations

    words related to understanding, comprehension, and knowledge

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "understand" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onies
    -0.72
    pmwiki
    -0.69
    nar
    -0.67
    ammy
    -0.67
    cgi
    -0.66
    ads
    -0.66
    onto
    -0.65
    emetery
    -0.64
    interstitial
    -0.63
    ulture
    -0.63
    POSITIVE LOGITS
     Understand
    0.87
     WHY
    0.85
    ably
    0.82
     how
    0.82
    ¿½
    0.78
     Leilan
    0.78
    ledge
    0.77
     understand
    0.77
     understands
    0.77
     why
    0.75
    Activations Density 0.025%

    No Known Activations