© 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. 4-RES-JB
    11. 2402
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a state of readiness or ripeness

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing quality or condition, particularly relating to edibility or state of being

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

    No Comments

    Negative Logits
     CLSID
    -0.84
    BOOK
    -0.73
    opers
    -0.73
    uyomi
    -0.72
    iazep
    -0.70
     patented
    -0.68
    rieving
    -0.66
    planes
    -0.66
    ciplinary
    -0.66
    rieve
    -0.66
    POSITIVE LOGITS
     ripe
    1.09
     fruits
    0.96
     fruit
    0.93
     tomatoes
    0.86
    atoes
    0.85
     strawberries
    0.81
     bananas
    0.76
     tomato
    0.76
    abouts
    0.76
     Gleaming
    0.75
    Activations Density 0.017%

    No Known Activations