© 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. 11-RES-JB
    11. 24436
    Prev
    Next
    INDEX
    Explanations

    references to various units of measurement, especially in the context of quantities or specifications

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to energy consumption or production

    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
     lax
    -0.66
     Leilan
    -0.66
    osaurus
    -0.62
     Reconstruction
    -0.61
     Situation
    -0.59
     pessim
    -0.56
     Wong
    -0.55
     ment
    -0.54
     Land
    -0.54
     interchange
    -0.54
    POSITIVE LOGITS
    pees
    1.26
    abytes
    1.13
    bps
    1.10
    bp
    1.07
    pg
    1.06
    ms
    1.03
    pm
    1.02
    ps
    1.00
    pi
    1.00
    ln
    1.00
    Activations Density 0.074%

    No Known Activations