© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 5482
    Prev
    Next
    INDEX
    Explanations

    negations, specifically the word "Not" followed by a high-activation word

    oai_token-act-pair · gpt-3.5-turbo

    phrases negating previous statements or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    States
    -0.71
    yout
    -0.65
    eers
    -0.64
    =(
    -0.64
    rift
    -0.63
    ãĥį
    -0.61
    FIG
    -0.59
     {:
    -0.59
     Handbook
    -0.58
    FI
    -0.57
    POSITIVE LOGITS
     anymore
    1.25
    withstanding
    1.12
     necessarily
    1.11
    icing
    1.08
    hin
    1.04
    epad
    1.00
     kidding
    0.94
    necess
    0.93
     sure
    0.93
    etheless
    0.93
    Activations Density 0.049%

    No Known Activations