© 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. 1-RES-JB
    11. 3936
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or geographical terms, with a focus on places in India

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Karnataka and related geographic names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    POS
    -0.69
    ÃĥÃĤÃĥÃĤ
    -0.64
    selage
    -0.63
    76561
    -0.62
     conc
    -0.61
    PRES
    -0.60
     decl
    -0.59
     scatter
    -0.59
     harmless
    -0.58
    ativity
    -0.58
    POSITIVE LOGITS
    ataka
    1.37
     Karn
    1.28
    ovan
    0.91
    wright
    0.86
    airo
    0.79
     lapt
    0.79
    lock
    0.79
    aby
    0.79
    aqu
    0.79
    ius
    0.79
    Activations Density 0.003%

    No Known Activations