© 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. 10457
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing contrasts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not just" indicating an expansion of ideas or concepts

    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
     largeDownload
    -0.79
    ĺħ
    -0.74
    oided
    -0.71
    »Ĵ
    -0.70
    find
    -0.66
    ller
    -0.66
    ixel
    -0.66
     Mushroom
    -0.64
    cember
    -0.64
    lain
    -0.63
    POSITIVE LOGITS
    ifiable
    1.30
    ifications
    0.99
     passively
    0.73
    ones
    0.72
     outright
    0.71
    itatively
    0.71
     kidding
    0.71
    IFIED
    0.70
     stra
    0.69
     coinc
    0.68
    Activations Density 0.025%

    No Known Activations