© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16431
    Prev
    Next
    INDEX
    Explanations

    dates within a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.84
    etsy
    -0.81
    uo
    -0.78
    oral
    -0.77
    lain
    -0.75
    riks
    -0.75
    rolet
    -0.75
    opping
    -0.74
    hem
    -0.73
     recess
    -0.73
    POSITIVE LOGITS
     Date
    1.09
     Dates
    1.03
    Date
    1.00
     Finder
    0.82
     Countdown
    0.80
    Time
    0.79
     Distance
    0.77
    date
    0.77
     inacc
    0.76
     Older
    0.76
    Activations Density 0.013%

    No Known Activations