© 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. 20826
    Prev
    Next
    INDEX
    Explanations

    keywords related to software development tasks and processes

    oai_token-act-pair · gpt-3.5-turbo

    actions and processes related to software deployment and updates

    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
    Johnson
    -0.84
    lance
    -0.78
    Bey
    -0.77
    interstitial
    -0.76
     Male
    -0.76
    conduct
    -0.74
    Male
    -0.73
     Ladies
    -0.72
     Illusion
    -0.72
     Hilton
    -0.71
    POSITIVE LOGITS
     dependencies
    1.29
     debugging
    1.25
     cached
    1.24
     updates
    1.23
     backups
    1.22
     debug
    1.20
     patches
    1.18
     repositories
    1.15
     GitHub
    1.15
     plugins
    1.15
    Activations Density 0.551%

    No Known Activations