© 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. 10-RES-JB
    11. 5841
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific time period just preceding an event

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" and its frequency in relation to other context

    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
    glomer
    -0.63
     disproportionately
    -0.60
    amia
    -0.59
    oidal
    -0.58
    amental
    -0.57
     Also
    -0.56
     seiz
    -0.55
     conserve
    -0.54
     Especially
    -0.54
     invari
    -0.53
    POSITIVE LOGITS
     weeks
    1.12
     days
    1.02
     months
    1.01
     hours
    0.95
    ifications
    0.84
     shy
    0.82
    ifiable
    0.81
    iciary
    0.80
    months
    0.79
    IFIED
    0.78
    Activations Density 0.056%

    No Known Activations