© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 13052
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comprehension, such as "understand that" or "understand why"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of comprehension or understanding about various topics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    chieve
    -0.76
    rouse
    -0.76
    mage
    -0.76
    estial
    -0.75
    gins
    -0.74
    idav
    -0.70
    adh
    -0.69
    aunder
    -0.67
    ifact
    -0.66
    izons
    -0.66
    POSITIVE LOGITS
     why
    0.76
     firsthand
    0.68
     frustration
    0.67
     personally
    0.65
     impat
    0.64
     apologizing
    0.64
     passionately
    0.64
     rejection
    0.64
    asper
    0.64
     sadness
    0.63
    Activations Density 0.095%

    No Known Activations