© 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 EvalsExportsinterp-engineNEWAPI 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. 2827
    Prev
    Next
    INDEX
    Explanations

    contractions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    negative contractions and phrases indicating failure or denial

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -1.26
    GGGGGGGG
    -0.99
    ©¶æ¥µ
    -0.90
    ģĸ
    -0.89
    senal
    -0.89
    CI
    -0.88
     practition
    -0.88
    EStream
    -0.88
    Ĥİ
    -0.87
    OTO
    -0.86
    POSITIVE LOGITS
     occur
    1.17
     satisfy
    1.13
     happen
    1.12
     pan
    1.12
     appease
    1.09
     resonate
    1.08
     material
    1.07
     sit
    1.03
     elicit
    1.02
     translate
    1.01
    Activations Density 0.123%

    No Known Activations