© 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. 3-RES-JB
    11. 16107
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the quality or condition of an object, such as "ripe," "juicy," and "rotten."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ripeness and decay, particularly in relation to foods and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.77
     CLSID
    -0.77
    opers
    -0.73
    BOOK
    -0.71
    iazep
    -0.71
    riber
    -0.69
    aida
    -0.67
    rieving
    -0.67
    OTO
    -0.67
    otte
    -0.66
    POSITIVE LOGITS
     ripe
    1.16
     fruit
    1.01
     fruits
    0.99
     tomatoes
    0.83
    fruit
    0.82
     strawberries
    0.77
     bananas
    0.76
     mango
    0.76
     grapes
    0.74
     tomato
    0.73
    Activations Density 0.004%

    No Known Activations