© 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 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. 7-RES-JB
    11. 20898
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.80
     Invention
    -0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    ãĤ¨ãĥ«
    -0.67
     someday
    -0.67
    UTF
    -0.67
    ert
    -0.62
    ventus
    -0.61
    Fac
    -0.59
    utf
    -0.59
    POSITIVE LOGITS
     devoted
    0.75
    iversary
    0.73
     PDT
    0.73
     holidays
    0.70
    eve
    0.70
     elapsed
    0.69
    urst
    0.68
    endars
    0.66
    ONY
    0.65
     mourning
    0.65
    Activations Density 0.266%

    No Known Activations