© 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. 7-RES-JB
    11. 9539
    Prev
    Next
    INDEX
    Explanations

    words related to changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "become" to indicate changes or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inarily
    -0.80
    oning
    -0.73
    ength
    -0.72
    inately
    -0.70
    erity
    -0.69
    bell
    -0.68
    idth
    -0.66
    aging
    -0.65
     Cran
    -0.64
    yip
    -0.64
    POSITIVE LOGITS
     extinct
    0.96
     obsolete
    0.93
     entangled
    0.93
     unman
    0.87
     accustomed
    0.86
     embroiled
    0.84
     clearer
    0.83
     irrelevant
    0.82
     synonymous
    0.82
     indistinguishable
    0.82
    Activations Density 0.053%

    No Known Activations