© 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. 3405
    Prev
    Next
    INDEX
    Explanations

    keywords related to data management, software development, technology jobs, surveillance equipment, and safety standards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data management and analytics

    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
    pload
    -0.61
     mummy
    -0.55
     chromos
    -0.52
     todd
    -0.51
     mockery
    -0.51
    姫
    -0.50
    umatic
    -0.50
     stroke
    -0.50
    ãģ£
    -0.50
     captcha
    -0.50
    POSITIVE LOGITS
    ateurs
    0.63
    posium
    0.57
    urus
    0.57
    ament
    0.57
    indust
    0.55
     Loren
    0.52
     Directorate
    0.52
    reements
    0.52
     headquartered
    0.52
    ":["
    0.51
    Activations Density 1.173%

    No Known Activations