© 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. 6308
    Prev
    Next
    INDEX
    Explanations

    specific references and citations, such as titles, chapters, and sections in documents

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, references, and document structure elements

    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
     opin
    -0.64
    soever
    -0.63
     murd
    -0.62
     detractors
    -0.60
    oday
    -0.60
     opinions
    -0.59
    '?
    -0.58
     biomedical
    -0.57
     ardent
    -0.57
     sentiments
    -0.57
    POSITIVE LOGITS
    20439
    0.85
    ãĥ´ãĤ¡
    0.78
    sbm
    0.78
    035
    0.76
    000
    0.74
    士
    0.73
    045
    0.71
    hov
    0.71
    éĹĺ
    0.70
     Tile
    0.69
    Activations Density 0.231%

    No Known Activations