© 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. 9-RES-JB
    11. 9943
    Prev
    Next
    INDEX
    Explanations

    verbs related to progression or change over time

    oai_token-act-pair · gpt-3.5-turbo

    actions or processes that indicate change or development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dug
    -0.57
     Vote
    -0.57
    USS
    -0.57
    idelines
    -0.56
    pictured
    -0.54
    Phill
    -0.54
     Administrative
    -0.52
    Enough
    -0.52
    boa
    -0.52
     Mandatory
    -0.51
    POSITIVE LOGITS
     spontaneously
    1.17
     whenever
    1.15
     when
    1.05
     unpredict
    0.97
     unconsciously
    0.93
     gradually
    0.93
    amorph
    0.92
     naturally
    0.92
    when
    0.91
     progressively
    0.90
    Activations Density 0.519%

    No Known Activations