© 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. 7297
    Prev
    Next
    INDEX
    Explanations

    references to the location "Napoli"

    oai_token-act-pair · gpt-3.5-turbo

    references to Napa Valley and its associated entities

    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
     Gemini
    -0.75
     Carbuncle
    -0.75
    worldly
    -0.74
    _____
    -0.72
    ______
    -0.72
    ³³³
    -0.69
    primary
    -0.68
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    RECT
    -0.67
    ~~
    -0.67
    POSITIVE LOGITS
    oleon
    1.29
    olit
    1.16
    alm
    1.14
    olitan
    1.05
     Nap
    1.04
    erville
    0.97
    Nap
    0.95
    ixels
    0.82
    iece
    0.79
    olini
    0.78
    Activations Density 0.010%

    No Known Activations