© 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. 9943
    Prev
    Next
    INDEX
    Explanations

    textual patterns that likely do not have a specific meaning or purpose, possibly related to errors or noise in the data

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to questioning or seeking clarification

    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
    hester
    -0.90
    etsy
    -0.88
    ère
    -0.77
    dylib
    -0.77
    Detect
    -0.76
    ARDIS
    -0.74
    oola
    -0.74
    AMY
    -0.73
    weeney
    -0.71
     Betsy
    -0.71
    POSITIVE LOGITS
     Protoss
    1.50
     Zerg
    1.45
     Starcraft
    1.41
     StarCraft
    1.36
     GSL
    1.26
     BW
    1.26
     Terran
    1.20
     Moder
    1.20
     MLG
    1.12
     WCS
    1.11
    Activations Density 0.093%

    No Known Activations