© 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. 0-RES-JB
    11. 15176
    Prev
    Next
    INDEX
    Explanations

    the word "ast" followed by a number, possibly related to the word "astute."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to astrology and astute analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mellon
    -0.77
    skirts
    -0.75
    =\"
    -0.72
     Regina
    -0.71
    verson
    -0.66
     burgers
    -0.66
     jeans
    -0.66
     Rita
    -0.65
     Ribbon
    -0.64
     Beef
    -0.64
    POSITIVE LOGITS
     ast
    3.95
    Ast
    1.96
     Ast
    1.88
     Astro
    1.44
     Astral
    1.40
     astroph
    1.27
     AST
    1.22
     astronomer
    1.13
     astronomy
    1.13
     Astron
    1.13
    Activations Density 0.018%

    No Known Activations