© 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. 4858
    Prev
    Next
    INDEX
    Explanations

    mentions of controversy or political/ethical stances in written text

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

    the word "that" in various contexts, indicating it may be looking for clauses or essential information in sentences

    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
    00007
    -0.66
    oret
    -0.66
    ãĥ³ãĤ¸
    -0.65
     Pwr
    -0.63
    ouch
    -0.63
    roach
    -0.62
    iots
    -0.62
    hip
    -0.60
    wire
    -0.59
    iscover
    -0.59
    POSITIVE LOGITS
     accompanies
    1.38
     arises
    1.20
     awaits
    1.19
     comes
    1.19
     entails
    1.18
     emerges
    1.11
     exists
    1.11
     surrounds
    1.08
     occurs
    1.08
     accompany
    1.07
    Activations Density 0.179%

    No Known Activations