© 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. 9-RES-JB
    11. 11729
    Prev
    Next
    INDEX
    Explanations

    dates written in ordinal form

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "of" and specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.67
    BILITIES
    -0.66
    erella
    -0.65
    alone
    -0.65
    RESULTS
    -0.62
    Items
    -0.61
    venge
    -0.60
    aryn
    -0.60
    gap
    -0.59
    IUM
    -0.58
    POSITIVE LOGITS
    teenth
    0.89
     July
    0.74
    cember
    0.68
     October
    0.67
     August
    0.67
     January
    0.66
    clock
    0.66
     September
    0.65
     December
    0.65
     November
    0.64
    Activations Density 0.105%

    No Known Activations