© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11282
    Prev
    Next
    INDEX
    Explanations

    titles or phrases containing the word "Dawn"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "dawn" in various contexts

    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
    ttle
    -0.77
    uana
    -0.71
    inates
    -0.68
    vant
    -0.67
    RED
    -0.67
    amins
    -0.65
    berus
    -0.65
    atable
    -0.65
    ======
    -0.65
    estyles
    -0.64
    POSITIVE LOGITS
    ing
    0.99
    bringer
    0.95
    star
    0.85
    hower
    0.84
    flower
    0.83
    walker
    0.82
    moon
    0.81
    forest
    0.78
    theless
    0.77
    fall
    0.77
    Activations Density 0.041%

    No Known Activations