© 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. 3552
    Prev
    Next
    INDEX
    Explanations

    scientific research terms related to data analysis and measurement

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific research methods and discoveries

    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
    Boss
    -0.78
     Promotion
    -0.75
    ardless
    -0.75
    _-
    -0.74
    obook
    -0.72
    ocracy
    -0.71
     Economy
    -0.71
     Winners
    -0.70
    disabled
    -0.69
    acia
    -0.69
    POSITIVE LOGITS
     measurements
    1.55
     microsc
    1.47
     infrared
    1.42
     telescopes
    1.41
     microscopic
    1.36
     isot
    1.30
     ultraviolet
    1.29
     microscope
    1.27
     MRI
    1.27
     imaging
    1.26
    Activations Density 0.368%

    No Known Activations