© 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. 6-RES-JB
    11. 9656
    Prev
    Next
    INDEX
    Explanations

    adjectives describing magnitude or high intensity

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that describe popularity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igi
    -0.75
    ensing
    -0.74
    ebin
    -0.72
    icip
    -0.70
    ties
    -0.67
    iem
    -0.67
    iture
    -0.66
    icipated
    -0.66
    oslov
    -0.65
     Continued
    -0.64
    POSITIVE LOGITS
     Important
    0.83
     underrated
    0.80
     profitable
    0.74
     beneficial
    0.74
     impractical
    0.73
     important
    0.70
     satisfying
    0.70
     rewarding
    0.69
     Awesome
    0.68
     fascinating
    0.68
    Activations Density 0.049%

    No Known Activations