© 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. 10-RES-JB
    11. 13776
    Prev
    Next
    INDEX
    Explanations

    technical terms related to performance enhancement or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to stability and efficiency 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
     originals
    -0.77
    archive
    -0.74
    swick
    -0.71
    artisan
    -0.70
     Ago
    -0.69
    代
    -0.69
     Tanz
    -0.65
    ãĥ³ãĤ¸
    -0.64
    ãĥĦ
    -0.63
     prince
    -0.62
    POSITIVE LOGITS
    factor
    1.07
     inherent
    0.98
     decreases
    0.96
     decreased
    0.90
    effic
    0.89
     affects
    0.86
    Increased
    0.85
     Increases
    0.85
     increases
    0.83
     thresholds
    0.82
    Activations Density 0.468%

    No Known Activations