© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    phrases related to objects or items

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

    references to pillows and related items or concepts

    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
    elist
    -0.71
    chi
    -0.65
    osta
    -0.61
     ENT
    -0.60
     variables
    -0.60
    yahoo
    -0.58
    worldly
    -0.58
     EntityItem
    -0.57
    lia
    -0.56
    lim
    -0.56
    POSITIVE LOGITS
    oried
    1.22
    ows
    1.13
    ory
    1.03
    ayers
    1.01
    aging
    0.93
    ared
    0.88
    AGE
    0.87
    boxes
    0.87
    owed
    0.86
    arer
    0.85
    Activations Density 0.158%

    No Known Activations