© 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. 7-RES-JB
    11. 7916
    Prev
    Next
    INDEX
    Explanations

    numerical figures and scientific notations within figures in a research context

    oai_token-act-pair · gpt-3.5-turbo

    references to figures or data points within a scientific or technical context

    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
    panic
    -0.74
     imperson
    -0.73
     academy
    -0.73
     perjury
    -0.67
     supernatural
    -0.67
    ecided
    -0.67
     Inquisition
    -0.66
     affairs
    -0.66
    uminati
    -0.65
     vig
    -0.65
    POSITIVE LOGITS
    Figure
    1.00
     largeDownload
    0.98
     illustrates
    0.86
    fig
    0.83
     Exhibit
    0.80
    below
    0.78
    ħĭ
    0.78
     Figure
    0.78
    figure
    0.77
    Fig
    0.77
    Activations Density 0.055%

    No Known Activations