© 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. 10-RES-JB
    11. 4788
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or conditions in the past that have had an impact on the present

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "past."

    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
    hyde
    -0.66
    oya
    -0.65
    wagon
    -0.65
    unk
    -0.64
    starting
    -0.61
    atism
    -0.61
    hat
    -0.61
    ucker
    -0.60
     Franch
    -0.59
    roots
    -0.59
    POSITIVE LOGITS
    ebin
    1.44
     decade
    1.38
     few
    1.27
     couple
    1.23
     tense
    1.20
     fortnight
    1.17
     month
    1.11
     week
    1.09
     year
    1.07
     century
    1.01
    Activations Density 0.032%

    No Known Activations