© 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 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. 6-RES-JB
    11. 7820
    Prev
    Next
    INDEX
    Explanations

    words related to understanding or comprehending concepts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "grasp" and related themes of understanding or control

    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
    ————
    -0.68
    onym
    -0.67
    xual
    -0.65
    ftime
    -0.64
    study
    -0.63
     Gentle
    -0.62
    escal
    -0.62
    grading
    -0.62
    audi
    -0.62
    resso
    -0.61
    POSITIVE LOGITS
     grasp
    0.98
     grasping
    0.95
    fully
    0.87
    ingly
    0.86
     grasped
    0.85
    craft
    0.82
    FUL
    0.78
    hold
    0.78
    footed
    0.77
    ifully
    0.76
    Activations Density 0.033%

    No Known Activations