© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 21799
    Prev
    Next
    INDEX
    Explanations

    words expressing surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    references to expressions of disappointment or discontent

    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
    •layer 11 - surprise

    No Comments

    Negative Logits
     warp
    -0.70
     wedge
    -0.69
     killer
    -0.68
     pile
    -0.67
     Warp
    -0.65
     catapult
    -0.64
     Kill
    -0.64
     Swarm
    -0.64
     KILL
    -0.63
     plunder
    -0.63
    POSITIVE LOGITS
    intend
    1.03
    agree
    1.00
    reci
    0.99
    felt
    0.95
    ulty
    0.92
    icip
    0.91
    itely
    0.90
    recomm
    0.89
    uly
    0.89
    highly
    0.88
    Activations Density 0.251%

    No Known Activations