© 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. 3-RES-JB
    11. 84
    Prev
    Next
    INDEX
    Explanations

    phrases related to the eventual outcome or final decision of a situation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ultimately."

    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
     newsletters
    -0.73
     Warm
    -0.68
     Wee
    -0.66
    bara
    -0.64
     Frog
    -0.63
     Sul
    -0.62
    names
    -0.60
     Willie
    -0.59
     mouths
    -0.58
     Keen
    -0.58
    POSITIVE LOGITS
    é¾įå
    0.80
     culmin
    0.78
    wcs
    0.78
     decided
    0.76
    redits
    0.72
     decide
    0.71
     opted
    0.71
    urable
    0.70
     assimil
    0.69
     satisfying
    0.69
    Activations Density 0.011%

    No Known Activations