© 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. 23293
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of being first or early

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "first-round" contexts in competitions or selections

    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
     mars
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.61
     shroud
    -0.60
    âĸĵ
    -0.59
    âĶģ
    -0.57
     Bullets
    -0.57
    âĸĴ
    -0.56
    MENTS
    -0.56
     Blanc
    -0.54
     contrary
    -0.54
    POSITIVE LOGITS
    ever
    1.20
    generation
    1.13
    degree
    1.02
    born
    1.02
    class
    0.99
    timer
    0.98
    round
    0.96
    time
    0.95
    century
    0.94
    edition
    0.94
    Activations Density 0.029%

    No Known Activations