© 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. 11-RES-JB
    11. 7584
    Prev
    Next
    INDEX
    Explanations

    keywords related to time, particularly numerical indications of time like periods and minutes

    oai_token-act-pair · gpt-3.5-turbo

    references to periods and phases in a game

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leaks
    -0.67
    eus
    -0.66
     Limits
    -0.62
    mbuds
    -0.61
    shows
    -0.61
    lihood
    -0.59
     winters
    -0.59
    comes
    -0.59
    issance
    -0.59
     nightmares
    -0.58
    POSITIVE LOGITS
     inning
    1.18
     quarter
    1.05
     minute
    0.99
     innings
    0.88
    inning
    0.81
    minute
    0.81
     frame
    0.80
     round
    0.79
     half
    0.77
    rium
    0.77
    Activations Density 0.061%

    No Known Activations