© 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. 3-RES-JB
    11. 607
    Prev
    Next
    INDEX
    Explanations

    capitalized city names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically place names or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hex
    -0.76
    mia
    -0.75
    ax
    -0.72
    works
    -0.72
    este
    -0.71
    hee
    -0.70
    lder
    -0.68
    legal
    -0.68
    gem
    -0.67
    illus
    -0.67
    POSITIVE LOGITS
    FORM
    1.41
    OUS
    1.41
    OUN
    1.40
    LINE
    1.36
    OL
    1.33
    ESS
    1.32
    INE
    1.32
    GROUND
    1.32
    ISH
    1.32
    IST
    1.31
    Activations Density 0.054%

    No Known Activations