© 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. 6-RES-JB
    11. 5003
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking or food preparation techniques involving roasting or toasting

    oai_token-act-pair · gpt-3.5-turbo

    foods and cooking methods specifically related to roasting or toasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otiation
    -0.89
    pheus
    -0.83
    hov
    -0.83
    asive
    -0.77
    ologne
    -0.72
    ciplinary
    -0.71
    earcher
    -0.70
    chy
    -0.68
    fighting
    -0.67
    etheless
    -0.67
    POSITIVE LOGITS
     Tycoon
    0.92
    asting
    0.86
     Delicious
    0.83
    rophe
    0.79
    velt
    0.79
    osaurus
    0.77
     toast
    0.76
    cake
    0.75
    âĶĢâĶĢâĶĢâĶĢ
    0.75
    osterone
    0.73
    Activations Density 0.041%

    No Known Activations