© 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. 2079
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disappointment or dissatisfaction

    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
     recogn
    -0.69
     coll
    -0.66
     lone
    -0.62
     nearest
    -0.62
     Moss
    -0.61
     ostr
    -0.61
     patched
    -0.60
     Koch
    -0.60
     CMS
    -0.59
     shack
    -0.59
    POSITIVE LOGITS
    ľ
    1.48
    ¬
    1.45
    ĸ
    1.35
    Ł
    1.25
    ķ
    1.24
    ı
    1.21
    ł
    1.21
    ¦
    1.21
    ¤
    1.19
    ¡
    1.19
    Activations Density 0.171%

    No Known Activations