© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    time durations expressed in numerical form

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with quantities or durations

    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
     Caption
    -0.69
    rike
    -0.68
    anka
    -0.67
     pse
    -0.65
    agame
    -0.65
    ragon
    -0.65
    ishop
    -0.58
    anian
    -0.58
    amaru
    -0.57
    buffer
    -0.57
    POSITIVE LOGITS
     reasons
    1.39
     years
    1.38
     months
    1.36
     hours
    1.36
     consecutive
    1.34
     weeks
    1.33
     days
    1.26
     purposes
    1.21
    months
    1.19
     nights
    1.18
    Activations Density 0.095%

    No Known Activations