© 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. 20558
    Prev
    Next
    INDEX
    Explanations

    words related to sharpness, accuracy, and precision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ac" in various contexts

    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
     Cors
    -0.64
    enger
    -0.64
     Saga
    -0.62
     CMS
    -0.60
    WT
    -0.58
     Prospect
    -0.57
     Shutterstock
    -0.57
    ISH
    -0.56
    ENG
    -0.56
     Parks
    -0.56
    POSITIVE LOGITS
    robat
    1.27
    uity
    1.17
    hes
    1.16
    erb
    1.15
    umen
    1.10
    orns
    1.10
    oust
    1.09
    qus
    1.06
    aution
    1.06
    ritical
    1.05
    Activations Density 0.018%

    No Known Activations