© 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 EvalsExportsinterp-engineNEWAPI 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. 15352
    Prev
    Next
    INDEX
    Explanations

    words related to success or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific category or type of product, particularly coffee or cappuccino

    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
     travelers
    -0.66
     travellers
    -0.64
     cons
    -0.63
     Hunt
    -0.62
     ministers
    -0.61
     prey
    -0.60
     translated
    -0.60
     keeper
    -0.60
     wise
    -0.60
     Ali
    -0.59
    POSITIVE LOGITS
    ucc
    4.86
     Bucc
    1.29
    ucci
    1.22
    uc
    1.14
    uci
    1.12
    uzz
    1.01
    uca
    0.96
    alach
    0.95
    undy
    0.92
    acc
    0.89
    Activations Density 0.008%

    No Known Activations