© 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. 2-RES-JB
    11. 19801
    Prev
    Next
    INDEX
    Explanations

    mentions of speed or quickness

    oai_token-act-pair · gpt-3.5-turbo

    references to speed or quickness in actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arov
    -0.81
    liga
    -0.78
    oral
    -0.77
    rights
    -0.74
    mberg
    -0.74
    ı
    -0.72
    pty
    -0.71
     Rights
    -0.71
     Shame
    -0.71
    sym
    -0.70
    POSITIVE LOGITS
     paced
    1.21
     than
    0.98
     Faster
    0.95
     lear
    0.92
     speeds
    0.91
     acceleration
    0.87
    idious
    0.86
     depreciation
    0.86
     Than
    0.85
     acceler
    0.80
    Activations Density 0.009%

    No Known Activations