© 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. 12-RES-JB
    11. 2550
    Prev
    Next
    INDEX
    Explanations

    phrases related to the condition, quality, or performance of objects

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    actions related to performance and condition in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    astern
    -0.80
    ewitness
    -0.78
    76561
    -0.67
    SPONSORED
    -0.64
    é¾įå
    -0.64
     Ending
    -0.64
    gypt
    -0.63
    oldown
    -0.63
    ¿½
    -0.63
    getting
    -0.62
    POSITIVE LOGITS
     smoothly
    1.31
     flaw
    1.20
     reliably
    1.15
     beautifully
    1.13
     nicely
    1.10
     smoother
    1.06
     satisf
    1.00
     wonderfully
    0.98
     properly
    0.95
     perfectly
    0.94
    Activations Density 0.287%

    No Known Activations