© 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. 9-RES-JB
    11. 5069
    Prev
    Next
    INDEX
    Explanations

    phrases related to event scheduling

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating the absence of events or activities

    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
    ĺħ
    -0.73
     nonetheless
    -0.61
    º
    -0.61
    Honest
    -0.59
    ĩ
    -0.59
    «ĺ
    -0.59
    ļé
    -0.58
     gist
    -0.58
    llah
    -0.58
     blat
    -0.57
    POSITIVE LOGITS
     adjourn
    0.84
     hiatus
    0.76
     Mondays
    0.74
     booked
    0.74
    Tickets
    0.71
     Sundays
    0.71
     postponed
    0.70
     discontinued
    0.70
     attendance
    0.68
     wheelchair
    0.67
    Activations Density 1.411%

    No Known Activations