© 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. 1-RES-JB
    11. 21689
    Prev
    Next
    INDEX
    Explanations

    keywords related to perfumes or scents

    oai_token-act-pair · gpt-3.5-turbo

    references to perfumes and related products

    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
    reau
    -0.88
    rained
    -0.87
    eer
    -0.80
    plex
    -0.78
    rack
    -0.76
    ulic
    -0.75
    rent
    -0.75
    lich
    -0.75
    ually
    -0.73
    rences
    -0.73
    POSITIVE LOGITS
     prol
    0.84
     Prol
    0.82
    otypes
    0.80
    otype
    0.80
    ophe
    0.78
    otaur
    0.76
    ogue
    0.74
     PF
    0.74
    éĹĺ
    0.72
    iminary
    0.72
    Activations Density 0.024%

    No Known Activations