© 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. 20808
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations or political entities

    oai_token-act-pair · gpt-3.5-turbo

    significant references to the United States and associated concepts

    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
     nurture
    -0.60
    pired
    -0.59
     groom
    -0.59
     outskirts
    -0.58
    ocado
    -0.57
     apparel
    -0.57
     Wear
    -0.56
    ienced
    -0.56
     luxury
    -0.56
     lifelong
    -0.55
    POSITIVE LOGITS
    :[
    1.39
     stating
    1.20
    :]
    1.17
    *:
    1.15
     wherein
    1.13
    :,
    1.10
    :"
    1.08
     whereby
    1.06
     noting
    1.05
    :(
    1.05
    Activations Density 0.453%

    No Known Activations