© 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. 3078
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific action or process being discussed

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

    phrases indicating focus or central themes in a narrative

    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
    anka
    -0.59
     ILCS
    -0.51
    umar
    -0.50
     slit
    -0.49
     tatt
    -0.46
    Number
    -0.46
    aren
    -0.46
     coerced
    -0.46
    olean
    -0.45
     Guinness
    -0.45
    POSITIVE LOGITS
     around
    1.04
     mainly
    0.84
     primarily
    0.84
     heavily
    0.81
     specifically
    0.80
     squarely
    0.74
     solely
    0.74
     largely
    0.73
     entirely
    0.73
     mostly
    0.72
    Activations Density 0.182%

    No Known Activations