© 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. 4-RES-JB
    11. 6531
    Prev
    Next
    INDEX
    Explanations

    terms related to academic fields or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to academic disciplines and institutions related to sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Islanders
    -0.69
    usher
    -0.67
    irth
    -0.66
    own
    -0.66
    owicz
    -0.64
    rel
    -0.63
    erous
    -0.62
    agements
    -0.61
    template
    -0.60
    leg
    -0.60
    POSITIVE LOGITS
     Sciences
    1.05
     sciences
    0.95
    ource
    0.87
     mathemat
    0.87
     faculties
    0.81
    creen
    0.81
    racuse
    0.80
    chool
    0.79
    terday
    0.79
    cules
    0.78
    Activations Density 0.023%

    No Known Activations