© 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. 7904
    Prev
    Next
    INDEX
    Explanations

    words related to intelligence, investigation, and reporting

    oai_token-act-pair · gpt-3.5-turbo

    references to repetitive actions or patterns

    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
     shoulders
    -0.61
     Cinderella
    -0.61
    qt
    -0.61
     pedest
    -0.57
     Panda
    -0.55
     plat
    -0.55
     minimized
    -0.54
    ä½ľ
    -0.54
     tray
    -0.53
    reau
    -0.53
    POSITIVE LOGITS
    igent
    0.86
    ACTION
    0.81
    herent
    0.80
    elta
    0.78
    entary
    0.76
    endo
    0.75
    unct
    0.73
    iencies
    0.72
    unt
    0.72
    ention
    0.71
    Activations Density 0.052%

    No Known Activations