© 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 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. 10-RES-JB
    11. 16541
    Prev
    Next
    INDEX
    Explanations

    actions or tasks that should be prioritized or done before anything else

    oai_token-act-pair · gpt-3.5-turbo

    the word "first" and its variations to indicate priority or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gould
    -0.65
    stead
    -0.63
     Sher
    -0.59
    âĶģ
    -0.59
    Quantity
    -0.59
     Doomsday
    -0.59
    pher
    -0.58
     Ell
    -0.57
     Tant
    -0.57
    IRC
    -0.55
    POSITIVE LOGITS
     responders
    1.15
     baseman
    1.14
     thing
    0.91
    hand
    0.88
     glance
    0.82
    aneously
    0.81
    ly
    0.80
     impression
    0.80
    ially
    0.79
     blush
    0.78
    Activations Density 0.043%

    No Known Activations