© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 24026
    Prev
    Next
    INDEX
    Explanations

    postal abbreviations associated with geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations, particularly U.S. states and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.85
    lihood
    -0.78
    henko
    -0.71
    andowski
    -0.69
    pour
    -0.68
    heet
    -0.67
    peat
    -0.66
    loads
    -0.66
    ror
    -0.65
    months
    -0.64
    POSITIVE LOGITS
    ARA
    0.74
     Dept
    0.72
    ./
    0.71
    JR
    0.70
    UL
    0.68
    LV
    0.68
    OTUS
    0.66
    GOP
    0.66
     Pavilion
    0.64
    ADA
    0.64
    Activations Density 0.039%

    No Known Activations