© 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. 7-RES-JB
    11. 5371
    Prev
    Next
    INDEX
    Explanations

    terms related to electrons and electron behavior in physics and materials science

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electron behavior in physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.79
    isSpecialOrderable
    -0.79
    DragonMagazine
    -0.76
    à¨
    -0.74
     à¨
    -0.73
    Iran
    -0.72
    quarters
    -0.71
     Grounds
    -0.70
     Alaska
    -0.69
    TIT
    -0.69
    POSITIVE LOGITS
     microscope
    0.85
     volts
    0.84
    ctrl
    0.83
    ucle
    0.76
     microsc
    0.75
     ions
    0.75
    ica
    0.74
    ically
    0.74
    isher
    0.74
    icals
    0.73
    Activations Density 0.033%

    No Known Activations