© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 8246
    Prev
    Next
    INDEX
    Explanations

    references to talent

    oai_token-act-pair · gpt-3.5-turbo

    references to skill or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    monitor
    -0.73
    resp
    -0.71
    omsky
    -0.67
    idon
    -0.67
    Ban
    -0.66
    osate
    -0.66
     POL
    -0.65
     Recon
    -0.64
    Includes
    -0.64
    én
    -0.63
    POSITIVE LOGITS
     talent
    3.72
     talents
    2.62
     Talent
    2.55
     talented
    1.84
     skill
    1.50
    tal
    1.47
     skills
    1.42
     creativity
    1.29
     knack
    1.29
     excellence
    1.21
    Activations Density 0.023%

    No Known Activations