© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 4205
    Prev
    Next
    INDEX
    Explanations

    time-related information, specifically the duration or starting point of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "since" in various contexts indicating a duration of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pta
    -0.80
    natureconservancy
    -0.78
    anie
    -0.76
    abus
    -0.76
    agy
    -0.69
    BILITIES
    -0.67
    potion
    -0.67
    Ds
    -0.66
    vous
    -0.66
    inki
    -0.64
    POSITIVE LOGITS
     inception
    1.13
     infancy
    1.10
     childhood
    1.02
     adolescence
    0.95
     1979
    0.93
     October
    0.93
     1999
    0.91
     November
    0.90
     1998
    0.90
     August
    0.90
    Activations Density 0.047%

    No Known Activations