© 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. 9-RES-JB
    11. 20719
    Prev
    Next
    INDEX
    Explanations

    indications of time frames in the recent past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly focusing on "the past."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.69
     outwe
    -0.64
    usercontent
    -0.63
    !.
    -0.63
    amen
    -0.62
    .[
    -0.61
     outweigh
    -0.61
     unemploy
    -0.60
     vulner
    -0.58
     choke
    -0.57
    POSITIVE LOGITS
     weeks
    0.77
     years
    0.77
     months
    0.69
    FAQ
    0.69
     YEAR
    0.68
     interview
    0.66
    ruary
    0.65
     decades
    0.64
    imester
    0.63
     1990
    0.63
    Activations Density 0.260%

    No Known Activations