© 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. 2783
    Prev
    Next
    INDEX
    Explanations

    descriptions of social events and interactions

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

    punctuation marks, particularly periods and commas

    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
     satell
    -1.47
     challeng
    -1.46
     volunte
    -1.37
     undermin
    -1.33
     confir
    -1.30
     tremend
    -1.29
     carbohyd
    -1.29
     nodd
    -1.27
    ¥ŀ
    -1.22
     suspic
    -1.21
    POSITIVE LOGITS
     Called
    1.35
     Located
    1.35
     Shortly
    1.34
     Specifically
    1.32
     Immediately
    1.32
     Named
    1.28
     Upon
    1.28
     Following
    1.27
     Initially
    1.26
     Referred
    1.24
    Activations Density 0.561%

    No Known Activations