© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 17296
    Prev
    Next
    INDEX
    Explanations

    events where someone holds a significant speaking or organizational role

    oai_token-act-pair · gpt-3.5-turbo

    instances of formal speaking engagements and presiding roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rated
    -0.65
    ster
    -0.65
    orough
    -0.64
    rug
    -0.64
    ter
    -0.64
    rified
    -0.64
     Petr
    -0.63
    worn
    -0.62
    gan
    -0.62
    rating
    -0.61
    POSITIVE LOGITS
     keynote
    1.27
     speaker
    1.01
     speakers
    0.85
     presentations
    0.82
     attendees
    0.81
    Topics
    0.81
    Panel
    0.79
     Speaker
    0.77
     BaseType
    0.74
     guests
    0.73
    Activations Density 0.011%

    No Known Activations