© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 1115
    Prev
    Next
    INDEX
    Explanations

    words related to speed and acceleration

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to speed and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rose
    -0.90
     Aph
    -0.84
     Lauder
    -0.84
    emn
    -0.81
     Rose
    -0.79
     Daly
    -0.77
     Nab
    -0.77
     Seym
    -0.76
     Hed
    -0.75
    emale
    -0.73
    POSITIVE LOGITS
     Speed
    2.02
     speed
    2.01
    Speed
    1.99
     Fast
    1.93
    speed
    1.87
    fast
    1.85
     fast
    1.84
     Slow
    1.83
    slow
    1.82
    Fast
    1.79
    Activations Density 0.244%

    No Known Activations