© 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. 18897
    Prev
    Next
    INDEX
    Explanations

    mentions of wearing gloves

    oai_token-act-pair · gpt-3.5-turbo

    words related to love

    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
     standard
    -0.73
     quiz
    -0.67
     fulfillment
    -0.66
     accounting
    -0.66
     cloud
    -0.65
     peer
    -0.64
     consortium
    -0.64
     recon
    -0.63
     Cron
    -0.62
     challenge
    -0.61
    POSITIVE LOGITS
    oves
    4.42
    ove
    2.28
    oved
    2.18
    oving
    2.03
    OV
    1.50
    oval
    1.38
    ovable
    1.37
    ovie
    1.34
    ovies
    1.30
    aves
    1.25
    Activations Density 0.004%

    No Known Activations