© 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. 22175
    Prev
    Next
    INDEX
    Explanations

    references to elements related to Bosnian geography and history

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bosnian" and related contexts or entities

    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
    yrinth
    -0.74
     Jarrett
    -0.62
     gratification
    -0.62
     PATH
    -0.60
    ITED
    -0.59
     Destroyer
    -0.58
     LIB
    -0.57
     BART
    -0.56
     scrimmage
    -0.55
     DSL
    -0.54
    POSITIVE LOGITS
    nian
    1.21
    well
    1.09
    combe
    1.03
    hing
    1.03
    coe
    1.03
    hens
    1.02
    colo
    0.96
    hea
    0.92
    co
    0.92
    herer
    0.91
    Activations Density 0.025%

    No Known Activations