© 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. 10-RES-JB
    11. 8513
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "appear."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appear" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dp
    -0.77
    aign
    -0.66
    Ws
    -0.65
    rpm
    -0.64
    shaw
    -0.64
     Mahjong
    -0.64
    ses
    -0.61
     Haram
    -0.59
    warts
    -0.59
    iott
    -0.59
    POSITIVE LOGITS
     onstage
    0.97
     alongside
    0.82
     poised
    0.79
     briefly
    0.78
     prominently
    0.76
    united
    0.75
    vind
    0.72
     victorious
    0.71
     intoxicated
    0.71
     beside
    0.69
    Activations Density 0.043%

    No Known Activations