© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    phrases related to various industries or business entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, entities, or organizations in business and industry contexts

    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
    spread
    -0.73
    ItemImage
    -0.69
    ̶
    -0.69
    ο
    -0.66
    SpaceEngineers
    -0.65
    Primary
    -0.64
    ãģĵ
    -0.64
    ilater
    -0.63
    ª
    -0.63
    SPONSORED
    -0.63
    POSITIVE LOGITS
     disagrees
    0.87
     meanwhile
    0.85
     agrees
    0.82
     believes
    0.80
     County
    0.78
     denies
    0.78
     welcomes
    0.75
     acknowledges
    0.75
     Profile
    0.75
     understands
    0.74
    Activations Density 0.481%

    No Known Activations