© 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. 0-RES-JB
    11. 20227
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location - Kentucky

    oai_token-act-pair · gpt-3.5-turbo

    the state codes of Kentucky (KY) and Kansas (KA) in the context of locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rar
    -0.82
    oqu
    -0.79
    reau
    -0.71
     gent
    -0.71
    apache
    -0.69
     pepper
    -0.69
    les
    -0.67
     Apache
    -0.66
    laim
    -0.66
     pencil
    -0.65
    POSITIVE LOGITS
    KY
    2.83
    KA
    2.76
     KY
    1.82
    KS
    1.78
    Ky
    1.54
    NH
    1.46
    NJ
    1.33
    NK
    1.32
    GH
    1.30
     TN
    1.28
    Activations Density 0.041%

    No Known Activations