© 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. 15124
    Prev
    Next
    INDEX
    Explanations

    acronyms related to time, specifically focusing on "AM" times

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the time designation "AM."

    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
     Vor
    -0.80
     drib
    -0.71
     priv
    -0.68
    erville
    -0.68
    atically
    -0.65
    virt
    -0.64
    viol
    -0.64
     toget
    -0.61
    à©
    -0.61
    letcher
    -0.60
    POSITIVE LOGITS
     AM
    3.74
     PM
    2.35
    AM
    2.03
    AMS
    1.58
     FM
    1.56
     AMA
    1.43
     Am
    1.43
     am
    1.36
    PM
    1.36
    am
    1.32
    Activations Density 0.010%

    No Known Activations