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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2789
    Prev
    Next
    INDEX
    Explanations

    keywords related to the introduction or focus of specific topics, especially when addressing important or core aspects of the subject matter

    oai_token-act-pair · gpt-3.5-turbo

    sequences that emphasize key points or main ideas in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.84
    ova
    -0.83
    span
    -0.73
    iage
    -0.72
    SPONSORED
    -0.72
    shown
    -0.71
    76561
    -0.71
    served
    -0.69
    trained
    -0.68
    HAM
    -0.68
    POSITIVE LOGITS
     basics
    1.28
     specifics
    1.05
     juicy
    1.04
     positives
    1.04
     Basics
    1.04
     nuts
    1.04
     actual
    1.02
     kicker
    1.02
     cru
    1.01
     topic
    1.00
    Activations Density 0.184%

    No Known Activations