© 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. 3-RES-JB
    11. 23618
    Prev
    Next
    INDEX
    Explanations

    words related to extraordinary or exceptionally well-made things

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with admiration and exceptional quality, particularly in art and nature

    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
    earcher
    -0.78
     intermittent
    -0.69
    ©¶æ
    -0.69
    quickShipAvailable
    -0.68
    pora
    -0.68
    heter
    -0.66
    ylene
    -0.65
    mber
    -0.65
    di
    -0.64
    ás
    -0.63
    POSITIVE LOGITS
    ously
    1.01
     marvel
    0.99
     wonders
    0.82
    Reviewed
    0.73
    Scroll
    0.69
     amazed
    0.67
    ifully
    0.67
    eries
    0.66
    wx
    0.66
    ulously
    0.66
    Activations Density 0.034%

    No Known Activations