© 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. 3343
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, specifically durations or timestamps

    oai_token-act-pair · gpt-3.5-turbo

    numerical references related to time and duration

    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
    onductor
    -0.70
     srf
    -0.69
    ufact
    -0.64
     Caption
    -0.64
    icter
    -0.62
    urden
    -0.61
     underside
    -0.60
    Prev
    -0.58
    Information
    -0.58
     depiction
    -0.57
    POSITIVE LOGITS
     bucks
    1.43
     guys
    1.10
     minutes
    1.08
     dudes
    1.08
     dollars
    1.08
     thousand
    1.08
     goddamn
    1.07
     fuckin
    1.04
     cents
    1.02
     mins
    1.01
    Activations Density 0.242%

    No Known Activations