© 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. 10-RES-JB
    11. 18947
    Prev
    Next
    INDEX
    Explanations

    comparisons between different groups or entities

    oai_token-act-pair · gpt-3.5-turbo

    comparative statements regarding rates or advantages in health and social science contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enthusi
    -0.65
     mathemat
    -0.64
     treaties
    -0.63
     Pok
    -0.62
    ovember
    -0.62
     Travels
    -0.61
     translator
    -0.60
     lia
    -0.59
     embassies
    -0.57
     revolutions
    -0.57
    POSITIVE LOGITS
     otherwise
    0.95
     placebo
    0.90
     passively
    0.84
    None
    0.83
     nons
    0.80
     merely
    0.79
     opposite
    0.79
    null
    0.77
     unaffected
    0.75
     nond
    0.75
    Activations Density 0.292%

    No Known Activations