© 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. 9-RES-JB
    11. 23517
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    references to gatherings or events involving multiple people

    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
     Decay
    -0.82
     blackmail
    -0.77
    piracy
    -0.75
    icide
    -0.71
     downgrade
    -0.71
     unsolved
    -0.69
     Suppose
    -0.68
     dependency
    -0.67
    obyl
    -0.67
    agate
    -0.67
    POSITIVE LOGITS
     attendees
    1.28
     applause
    1.19
     onstage
    1.11
     cheers
    1.08
     seated
    1.06
     chants
    1.03
     chanting
    1.03
     ceremon
    1.02
     podium
    1.01
     guests
    1.01
    Activations Density 1.459%

    No Known Activations