© 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. 8-RES-JB
    11. 19296
    Prev
    Next
    INDEX
    Explanations

    verbs related to becoming skilled or proficient in a task or field

    oai_token-act-pair · gpt-3.5-turbo

    words related to mastery and skill development

    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
    isSpecialOrderable
    -0.84
    ãĥ´
    -0.66
    usha
    -0.66
    iatus
    -0.64
     Helsinki
    -0.63
    idia
    -0.63
    Neigh
    -0.62
    grave
    -0.62
    soType
    -0.62
    aternity
    -0.61
    POSITIVE LOGITS
     mastery
    1.07
     mastering
    0.99
     mastered
    0.99
     dexterity
    0.99
     tricks
    0.96
     technique
    0.95
     patience
    0.95
     tact
    0.94
     navigating
    0.89
     manipulation
    0.87
    Activations Density 0.208%

    No Known Activations