© 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. 9604
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or interest in seeing something happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "would like to see" in various contexts

    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
    ÃŃa
    -0.77
     whistle
    -0.75
    alias
    -0.72
     Warning
    -0.66
    externalActionCode
    -0.66
    ãĥĦ
    -0.64
    spoken
    -0.64
    purpose
    -0.63
     tip
    -0.62
     Annotations
    -0.61
    POSITIVE LOGITS
    inelli
    0.82
    enance
    0.80
    oleon
    0.74
    dust
    0.74
     improvements
    0.74
     firsthand
    0.73
    awed
    0.71
     how
    0.71
    dogs
    0.70
     visions
    0.69
    Activations Density 0.076%

    No Known Activations