© 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. 0-RES-JB
    11. 13794
    Prev
    Next
    INDEX
    Explanations

    hygienic products related to oral care

    oai_token-act-pair · gpt-3.5-turbo

    items related to oral hygiene and dental care

    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
     NAD
    -0.65
    iating
    -0.65
     deficiency
    -0.64
     Swarm
    -0.64
     Polk
    -0.64
     tenants
    -0.62
     adjourn
    -0.61
     unanimous
    -0.61
     halftime
    -0.61
     Lenn
    -0.60
    POSITIVE LOGITS
    paste
    2.92
    past
    2.47
    brush
    2.41
    pick
    2.01
     fairy
    1.49
    write
    1.25
     Fairy
    1.21
    clip
    1.04
    aimon
    1.03
    anges
    1.01
    Activations Density 0.019%

    No Known Activations