© 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. 8-RES-JB
    11. 11070
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a specific part or section of something

    oai_token-act-pair · gpt-3.5-turbo

    references to specific parts or segments of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berus
    -0.71
     Skies
    -0.71
    ãĤī
    -0.66
    gently
    -0.64
    culosis
    -0.63
     Klux
    -0.60
     Arms
    -0.60
     commissions
    -0.60
    claimed
    -0.59
    leneck
    -0.59
    POSITIVE LOGITS
    ridge
    1.05
    ridges
    1.03
    ials
    1.00
    icular
    0.87
    meal
    0.86
    icle
    0.82
     thereof
    0.80
    icles
    0.79
    uring
    0.78
    aking
    0.76
    Activations Density 0.053%

    No Known Activations