© 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. 10-RES-JB
    11. 16647
    Prev
    Next
    INDEX
    Explanations

    names of events, people, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to presentations or discussions at conferences and events

    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
    usercontent
    -0.74
     forbid
    -0.73
     versa
    -0.70
    cache
    -0.70
    arently
    -0.69
     revenge
    -0.67
     somehow
    -0.66
     legitimately
    -0.65
     neglig
    -0.64
     bastard
    -0.63
    POSITIVE LOGITS
     keynote
    1.27
     presentations
    1.18
     Subcommittee
    1.11
     Wednesday
    1.07
     Tuesday
    1.07
     Thursday
    1.06
     subcommittee
    1.04
    Panel
    1.03
     conference
    1.00
     convened
    0.99
    Activations Density 0.523%

    No Known Activations