© 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. 8-RES-JB
    11. 4235
    Prev
    Next
    INDEX
    Explanations

    instructions or calls to action related to enabling or supporting JavaScript

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to enabling or configuring settings, particularly for JavaScript

    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
    Ö¼
    -0.73
    GoldMagikarp
    -0.70
    Ops
    -0.67
    Hop
    -0.65
    Downloadha
    -0.62
     Trends
    -0.59
    Beat
    -0.58
    EStreamFrame
    -0.57
    rontal
    -0.56
    olver
    -0.55
    POSITIVE LOGITS
     Javascript
    0.77
    edia
    0.73
     responsibly
    0.69
    emort
    0.68
     yourselves
    0.67
    taboola
    0.66
    ruary
    0.66
    ername
    0.66
     Monteneg
    0.65
    nce
    0.64
    Activations Density 0.071%

    No Known Activations