© 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. 10-RES-JB
    11. 8589
    Prev
    Next
    INDEX
    Explanations

    names with an Irish or Celtic origin

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "O'" in various contexts

    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
     eclipse
    -0.72
     applicable
    -0.70
    terday
    -0.66
    »Ĵ
    -0.65
     intimid
    -0.62
     indoors
    -0.61
     indo
    -0.59
     actionGroup
    -0.58
     dispersed
    -0.58
     snatch
    -0.57
    POSITIVE LOGITS
    Brien
    1.50
    Neill
    1.45
    Donnell
    1.44
    Malley
    1.43
    Connor
    1.38
    Leary
    1.35
    Reilly
    1.31
    Sullivan
    1.29
    Neal
    1.28
    Neil
    1.27
    Activations Density 0.019%

    No Known Activations