© 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. 10-RES-JB
    11. 10679
    Prev
    Next
    INDEX
    Explanations

    phrases related to talent or skills, specifically highlighting highly skilled individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with skilled and talented individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thur
    -0.84
    eda
    -0.81
    avia
    -0.76
    uer
    -0.74
    lik
    -0.73
    è£ħ
    -0.73
    eu
    -0.72
    utra
    -0.72
    isite
    -0.72
    ĸļ
    -0.71
    POSITIVE LOGITS
     individuals
    1.27
     professionals
    1.24
     young
    1.08
     minds
    1.02
     crafts
    0.97
     workers
    0.97
     entrepreneurs
    0.96
     musicians
    0.96
     volunteers
    0.96
     citiz
    0.95
    Activations Density 0.107%

    No Known Activations