© 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. 10-RES-JB
    11. 4735
    Prev
    Next
    INDEX
    Explanations

    keywords related to business and economics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic concepts and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charism
    -0.71
     NAACP
    -0.64
     contested
    -0.63
     conflicted
    -0.62
     Volks
    -0.62
     Holocaust
    -0.61
     unres
    -0.61
     lifelong
    -0.60
     glamorous
    -0.59
     intimidating
    -0.59
    POSITIVE LOGITS
    xit
    0.98
    vier
    0.93
    llan
    0.93
    dylib
    0.91
    xon
    0.89
    bots
    0.87
    anus
    0.87
    duino
    0.85
    ovo
    0.85
    inia
    0.84
    Activations Density 0.446%

    No Known Activations