© 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. 10-RES-JB
    11. 18994
    Prev
    Next
    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    specific days of the week and dates in the text

    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
    clusions
    -0.62
    omic
    -0.59
    push
    -0.58
    addons
    -0.57
    notations
    -0.57
     ])
    -0.56
    ãĥ¤
    -0.55
    HAHAHAHA
    -0.54
    UTF
    -0.54
    pires
    -0.54
    POSITIVE LOGITS
     aboard
    0.86
     at
    0.78
     near
    0.75
     inside
    0.74
     atop
    0.73
     outside
    0.73
     against
    0.72
     in
    0.72
     flanked
    0.71
     across
    0.69
    Activations Density 0.258%

    No Known Activations