© 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. 20828
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods, particularly "this year"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods, particularly in relation to "this year," "month," and "week."

    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
     bom
    -0.63
    00200000
    -0.62
    Unix
    -0.62
    aution
    -0.61
     Vim
    -0.60
    udeb
    -0.58
    enza
    -0.58
    otto
    -0.57
    rieg
    -0.57
    jong
    -0.57
    POSITIVE LOGITS
     rumors
    0.82
     when
    0.72
     announcing
    0.70
    tower
    0.68
     rumours
    0.66
    ripp
    0.63
     revealing
    0.63
     heels
    0.62
     Shank
    0.61
    flower
    0.60
    Activations Density 0.105%

    No Known Activations