© 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. 9-RES-JB
    11. 11381
    Prev
    Next
    INDEX
    Explanations

    the word "Dawn"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Dawn" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amins
    -0.81
    ATIONS
    -0.71
    ======
    -0.69
    asus
    -0.63
    asions
    -0.63
     ABE
    -0.63
    ========
    -0.63
    uana
    -0.62
    RED
    -0.62
     exha
    -0.61
    POSITIVE LOGITS
    bringer
    1.14
    guard
    0.97
    ing
    0.87
    star
    0.86
    hower
    0.84
    bach
    0.84
    flower
    0.83
    walker
    0.82
    iard
    0.80
     Arbor
    0.79
    Activations Density 0.049%

    No Known Activations