© 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. 2686
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to technology or medical devices

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

    punctuation and sentence endings

    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
     tremend
    -1.53
     satell
    -1.52
     carbohyd
    -1.44
     gobl
    -1.40
    ¥ŀ
    -1.40
     challeng
    -1.35
     confir
    -1.34
     tradem
    -1.33
     millenn
    -1.33
     volunte
    -1.33
    POSITIVE LOGITS
     Needless
    1.21
    ↵
    1.20
     Finally
    1.19
     Thankfully
    1.17
     Regardless
    1.17
     Ultimately
    1.17
     Nonetheless
    1.16
     Lastly
    1.15
     Fortunately
    1.15
     Luckily
    1.14
    Activations Density 0.714%

    No Known Activations