© 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. 9-RES-JB
    11. 19432
    Prev
    Next
    INDEX
    Explanations

    companies or entities involved in different situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating associations with companies or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivable
    -0.73
    lander
    -0.66
    ional
    -0.66
    Ble
    -0.66
    aning
    -0.65
    unning
    -0.64
    limited
    -0.62
    fml
    -0.61
     anywhere
    -0.61
     worsening
    -0.61
    POSITIVE LOGITS
     oversaw
    1.02
     governs
    1.00
     accompanies
    0.97
     oversees
    0.94
     comprise
    0.92
     spawned
    0.91
     owns
    0.86
     surrounds
    0.86
     mattered
    0.84
     preceded
    0.84
    Activations Density 0.193%

    No Known Activations