© 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. 11-RES-JB
    11. 13653
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Ger"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or term, likely related to a person or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     CPC
    -0.75
    eer
    -0.64
    eers
    -0.60
     Gemini
    -0.59
     rig
    -0.59
     inadequ
    -0.59
     Unic
    -0.58
     chained
    -0.58
     caps
    -0.57
     Samoa
    -0.57
    POSITIVE LOGITS
    iatric
    1.31
    iatrics
    1.19
    mination
    1.19
    anium
    1.16
    usalem
    1.14
    rit
    1.08
    rera
    1.07
    bil
    1.06
    udo
    1.03
    anyl
    1.00
    Activations Density 0.034%

    No Known Activations