© 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. 1-RES-JB
    11. 17732
    Prev
    Next
    INDEX
    Explanations

    words related to intense desires or cravings, particularly of a physical or emotional nature

    oai_token-act-pair · gpt-3.5-turbo

    references to desire or craving, particularly in emotional or physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Doodle
    -0.76
    UGH
    -0.72
     reboot
    -0.69
    levision
    -0.64
    ACP
    -0.64
    semble
    -0.63
     toast
    -0.61
     Harlem
    -0.61
     Dame
    -0.61
     cryst
    -0.61
    POSITIVE LOGITS
    lust
    1.00
    s
    0.86
    rous
    0.85
    ivities
    0.83
    sburg
    0.82
    son
    0.82
    orical
    0.79
    atic
    0.78
    ime
    0.78
    swe
    0.77
    Activations Density 0.028%

    No Known Activations