© 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. 3131
    Prev
    Next
    INDEX
    Explanations

    phrases related to advancement, promotion, and pursuit of goals or ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to advancing or promoting ideas and knowledge

    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
     reluctantly
    -0.70
     abruptly
    -0.68
    pants
    -0.68
     disg
    -0.66
    closure
    -0.66
    soDeliveryDate
    -0.65
     evict
    -0.65
     lest
    -0.65
    Setup
    -0.65
    ucket
    -0.65
    POSITIVE LOGITS
     careers
    1.08
     creativity
    1.03
     talents
    1.01
     entrepreneurship
    1.00
     awareness
    0.99
     ideals
    0.99
     ideas
    0.98
     technologies
    0.96
     arts
    0.96
     literacy
    0.95
    Activations Density 0.374%

    No Known Activations