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

    Neuronpedia

    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. 4-RES-JB
    11. 22042
    Prev
    Next
    INDEX
    Explanations

    dates in the month of April

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific dates, particularly in April

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

    No Comments

    Negative Logits
    atem
    -0.76
    ancial
    -0.72
    perm
    -0.70
    ebook
    -0.66
    desc
    -0.65
    committee
    -0.64
     VIDEOS
    -0.61
    reb
    -0.60
    entials
    -0.60
    mercial
    -0.60
    POSITIVE LOGITS
     Fool
    1.00
    flower
    0.98
    nard
    0.91
    onna
    0.83
    berry
    0.80
     2019
    0.80
    eteenth
    0.80
     29
    0.75
     Madness
    0.75
     2015
    0.74
    Activations Density 0.020%

    No Known Activations