© 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. 1857
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "itive" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to adjectives and descriptors

    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
    soDeliveryDate
    -0.77
    FORE
    -0.75
     Fitzgerald
    -0.72
    ascular
    -0.72
    meal
    -0.69
    SUP
    -0.68
    Miller
    -0.68
    isle
    -0.67
     Sutherland
    -0.66
    ammed
    -0.66
    POSITIVE LOGITS
    itive
    1.29
    ly
    1.23
    itives
    1.00
    LY
    0.83
    lly
    0.83
     minded
    0.82
    itiveness
    0.80
    iveness
    0.76
    ELY
    0.76
    ety
    0.75
    Activations Density 0.017%

    No Known Activations