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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6197
    Prev
    Next
    INDEX
    Explanations

    information related to meetings, events, and schedules

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of meetings or events in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antibodies
    -0.71
     weaknesses
    -0.70
     patents
    -0.70
     veins
    -0.69
     mutations
    -0.69
     fibers
    -0.68
     fingerprints
    -0.67
     Species
    -0.67
     minerals
    -0.66
     equations
    -0.65
    POSITIVE LOGITS
     scheduled
    1.21
     hosted
    1.18
     convened
    1.13
     attended
    1.12
     billed
    1.08
     EVENT
    1.05
     chaired
    1.04
     conducted
    1.04
     postponed
    1.04
     attendees
    1.01
    Activations Density 0.598%

    No Known Activations