© 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. 3-RES-JB
    11. 5364
    Prev
    Next
    INDEX
    Explanations

    words related to technology performance issues, specifically focusing on lag and latency

    oai_token-act-pair · gpt-3.5-turbo

    terms related to delays and performance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.79
    ä½ľ
    -0.72
    IBLE
    -0.69
    KI
    -0.66
     Marketable
    -0.66
    cription
    -0.65
    ãĥ´ãĤ¡
    -0.65
     toget
    -0.63
    criptions
    -0.63
    )].
    -0.62
    POSITIVE LOGITS
     lag
    1.22
    oon
    1.13
    uten
    1.02
     Lag
    0.90
    arde
    0.85
    omorph
    0.83
    ering
    0.79
    lag
    0.79
    rang
    0.78
    gers
    0.78
    Activations Density 0.006%

    No Known Activations