© 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. 3409
    Prev
    Next
    INDEX
    Explanations

    information related to social behaviors and living habits of wasps

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

    information about social structures and behaviors in animal species

    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
    Force
    -0.76
    TeX
    -0.73
    brand
    -0.73
    ãĤ´
    -0.70
    ãĥīãĥ©
    -0.69
    ãĥ¼ãĥĨ
    -0.69
    ãĤ¡
    -0.68
    nikov
    -0.68
    ixel
    -0.68
    Ò
    -0.67
    POSITIVE LOGITS
     nests
    1.42
     captivity
    1.33
     habitats
    1.33
     nesting
    1.29
     hiber
    1.21
     freshwater
    1.15
     nest
    1.15
     habitat
    1.14
     caves
    1.14
     moist
    1.13
    Activations Density 0.268%

    No Known Activations