© 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. 11162
    Prev
    Next
    INDEX
    Explanations

    specific locations or entities, such as countries, universities, organizations, or sports teams

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations and names related to organizations or events

    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
     complementary
    -0.60
     lamented
    -0.60
     amassed
    -0.60
     resembled
    -0.59
     succumbed
    -0.57
     redirected
    -0.57
     discont
    -0.56
     volatile
    -0.56
     reprinted
    -0.56
     debilitating
    -0.56
    POSITIVE LOGITS
    âĢ
    1.33
    .''
    1.15
    ãĢ
    1.14
    .�
    1.12
    Ò
    1.08
    .?
    1.06
    _.
    1.05
    .</
    1.04
    âĿ
    1.03
    .ãĢį
    1.03
    Activations Density 0.797%

    No Known Activations