© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 13931
    Prev
    Next
    INDEX
    Explanations

    references to the geographical location "Kansas City"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Kansas and its cities

    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
     arte
    -0.77
     liner
    -0.76
     harbour
    -0.73
    ship
    -0.72
    amine
    -0.71
    ares
    -0.70
     analys
    -0.69
    ships
    -0.67
     proverb
    -0.65
     Tablet
    -0.64
    POSITIVE LOGITS
     Kansas
    3.65
    Kansas
    3.39
     Wichita
    2.38
     Missouri
    2.09
     Oklahoma
    2.08
     Kentucky
    1.83
     Iowa
    1.81
    Iowa
    1.80
     KC
    1.79
     Cincinnati
    1.77
    Activations Density 0.017%

    No Known Activations