© 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. 14880
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and industry processes, such as 'fuel', 'livestock feed', 'tax havens', and 'screenshot sequences'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various industries and legal aspects

    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
    ichen
    -0.72
    merce
    -0.72
    edin
    -0.70
    rity
    -0.70
    istries
    -0.68
    abases
    -0.68
    webkit
    -0.65
    Sym
    -0.64
    terness
    -0.63
    cture
    -0.62
    POSITIVE LOGITS
     progresses
    1.06
     accompan
    0.87
     conduit
    0.87
     replacement
    0.83
     intermediary
    0.78
     centerpiece
    0.77
     filler
    0.77
     substitute
    0.76
     adjunct
    0.76
     replacements
    0.75
    Activations Density 0.397%

    No Known Activations