© 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. 13892
    Prev
    Next
    INDEX
    Explanations

    words related to specific categories, such as food, locations, and political events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific societal issues or objects

    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
    Lear
    -0.61
    Recomm
    -0.57
     Afterwards
    -0.53
     Icar
    -0.51
    Reply
    -0.49
    ļé
    -0.49
     independ
    -0.49
     afterwards
    -0.49
     myster
    -0.48
    Reason
    -0.48
    POSITIVE LOGITS
     are
    1.30
     comprise
    1.25
     aren
    1.23
     constitute
    1.21
     have
    1.20
     deserve
    1.15
     belong
    1.13
     contain
    1.10
     abound
    1.10
     remain
    1.07
    Activations Density 0.464%

    No Known Activations