© 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. 9-RES-JB
    11. 10295
    Prev
    Next
    INDEX
    Explanations

    phrases expressing understanding or comprehension

    oai_token-act-pair · gpt-3.5-turbo

    expressions of understanding or confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    velt
    -0.65
    worthy
    -0.63
     foss
    -0.59
    erness
    -0.59
    haus
    -0.59
    agen
    -0.59
     feasibility
    -0.58
     ante
    -0.57
    yet
    -0.57
     Britann
    -0.57
    POSITIVE LOGITS
     bored
    0.98
     tired
    0.95
     annoyed
    0.93
     rid
    0.93
     distracted
    0.90
     punished
    0.86
     yelled
    0.84
     irritated
    0.83
     sucked
    0.82
     confused
    0.82
    Activations Density 0.080%

    No Known Activations