© 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. 0-RES-JB
    11. 395
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or points of interest

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itably
    -0.76
    pex
    -0.73
    ividual
    -0.71
    ufact
    -0.69
    rastructure
    -0.66
     withd
    -0.65
    ulk
    -0.64
    anmar
    -0.63
    ibliography
    -0.63
    mercial
    -0.62
    POSITIVE LOGITS
     at
    1.79
     At
    0.97
    at
    0.93
    At
    0.93
     AT
    0.91
     anywhere
    0.74
     in
    0.69
     during
    0.68
     on
    0.68
     @
    0.67
    Activations Density 0.179%

    No Known Activations