© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 23373
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack of comprehension or confusion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of comprehension or lack thereof

    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
    onies
    -0.74
    ammy
    -0.66
    nar
    -0.64
    jay
    -0.63
     downed
    -0.62
    onto
    -0.62
    emetery
    -0.61
     stunt
    -0.61
     sled
    -0.60
    drops
    -0.60
    POSITIVE LOGITS
     WHY
    0.90
     Understand
    0.87
     how
    0.82
    ably
    0.82
     Understanding
    0.79
     why
    0.79
     understand
    0.76
     understands
    0.75
    omatic
    0.74
    ¿½
    0.71
    Activations Density 0.030%

    No Known Activations