© 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. 4-RES-JB
    11. 22009
    Prev
    Next
    INDEX
    Explanations

    references to bottled water and canned food

    oai_token-act-pair · gpt-3.5-turbo

    references to bottled and canned food products

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

    No Comments

    Negative Logits
    nesota
    -0.99
    lihood
    -0.92
    rn
    -0.83
    lde
    -0.81
    alter
    -0.79
    ffield
    -0.79
    xual
    -0.76
    hov
    -0.75
    cloth
    -0.74
    holes
    -0.74
    POSITIVE LOGITS
     bottled
    0.93
    Catal
    0.79
    kamp
    0.70
    ãĤª
    0.70
     bananas
    0.69
    ificate
    0.68
     water
    0.68
    ãĥĥãĤ¯
    0.67
    ãĤ¢ãĥ«
    0.66
     peanuts
    0.66
    Activations Density 0.019%

    No Known Activations