© 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. 0-RES-JB
    11. 15361
    Prev
    Next
    INDEX
    Explanations

    the weekday "Thursday"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the day "Thursday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prototyp
    -0.71
     realise
    -0.70
     analogue
    -0.63
     realised
    -0.63
    Export
    -0.61
     replaced
    -0.60
     indexed
    -0.59
    types
    -0.58
    hess
    -0.58
    GP
    -0.57
    POSITIVE LOGITS
     Thursday
    3.24
     Wednesday
    2.95
     Friday
    2.84
    Thursday
    2.75
     Tuesday
    2.64
     Monday
    2.60
     Saturday
    2.49
    Wednesday
    2.42
    Friday
    2.36
     Sunday
    2.32
    Activations Density 0.019%

    No Known Activations