© 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. 8-RES-JB
    11. 12431
    Prev
    Next
    INDEX
    Explanations

    words related to defining or redefining concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to definitions and their nuances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.73
    athi
    -0.72
    ocamp
    -0.72
    rentice
    -0.71
    aptic
    -0.71
    ience
    -0.71
    rites
    -0.70
    orthy
    -0.70
    VERTISEMENT
    -0.70
    riter
    -0.70
    POSITIVE LOGITS
    initions
    0.91
     definitions
    0.91
    inition
    0.82
     defines
    0.81
     definition
    0.79
     defining
    0.79
    witz
    0.75
     defined
    0.73
     criteria
    0.72
     ambig
    0.72
    Activations Density 0.047%

    No Known Activations