© 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 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. 2-RES-JB
    11. 19636
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the ripeness of fruits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the quality and condition of food and living entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iazep
    -0.73
     CLSID
    -0.72
    BOOK
    -0.69
    addock
    -0.68
    respect
    -0.67
    uyomi
    -0.67
    rief
    -0.66
    opers
    -0.66
    aida
    -0.65
    lua
    -0.65
    POSITIVE LOGITS
     ripe
    1.19
     fruits
    0.94
     fruit
    0.92
     tomatoes
    0.84
     strawberries
    0.79
    atoes
    0.79
     Gleaming
    0.77
    ezvous
    0.74
    ishable
    0.74
    fruit
    0.74
    Activations Density 0.009%

    No Known Activations