© 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 EvalsExportsinterp-engineNEWAPI 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. 18939
    Prev
    Next
    INDEX
    Explanations

    phrases related to releasing new works or information

    oai_token-act-pair · gpt-3.5-turbo

    key details about individuals' careers and activities in the entertainment industry

    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
    Defense
    -0.76
    protection
    -0.75
     prejudice
    -0.73
    efficiency
    -0.72
     inadequate
    -0.72
    ItemTracker
    -0.71
    defense
    -0.71
     unfair
    -0.70
     allowance
    -0.69
    Newsletter
    -0.69
    POSITIVE LOGITS
     debuted
    1.26
     collaborated
    1.26
     onstage
    1.25
     premiered
    1.24
     cameo
    1.23
     collaborations
    1.21
     solo
    1.20
     teamed
    1.17
     toured
    1.17
     remix
    1.16
    Activations Density 0.499%

    No Known Activations