© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 3056
    Prev
    Next
    INDEX
    Explanations

    mention of future plans or actions by individuals

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

    references to personal pronouns, indicating active participation or connection in the narrative

    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
    OTOS
    -0.72
     Tide
    -0.66
     Fishing
    -0.65
    RAG
    -0.64
     Flowers
    -0.64
     Lunch
    -0.64
     srfAttach
    -0.63
     Alchemist
    -0.63
    ADVERTISEMENT
    -0.61
     Berks
    -0.60
    POSITIVE LOGITS
     dubbed
    1.14
     termed
    1.13
     dub
    1.06
     deems
    1.05
     deemed
    1.01
     likened
    1.00
     nicknamed
    1.00
     describes
    0.94
     attributed
    0.94
     interpreted
    0.91
    Activations Density 0.207%

    No Known Activations