© 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. 8-RES-JB
    11. 4231
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Sacramento

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sacramento."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ager
    -0.86
    aging
    -0.83
    agers
    -0.83
    enegger
    -0.77
    age
    -0.77
    agher
    -0.75
    enberg
    -0.74
    ily
    -0.73
    AGE
    -0.71
    aged
    -0.70
    POSITIVE LOGITS
    rament
    0.95
     Bee
    0.87
    Republic
    0.85
     Kings
    0.85
     Sacramento
    0.82
    char
    0.81
    Hunt
    0.76
     Republic
    0.76
    oslav
    0.75
     Kush
    0.74
    Activations Density 0.063%

    No Known Activations