© 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. 0-RES-JB
    11. 2864
    Prev
    Next
    INDEX
    Explanations

    schedules and substances classified under Schedule 9

    oai_token-act-pair · gpt-3.5-turbo

    references to scheduled events or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deflect
    -0.80
    dding
    -0.76
    chest
    -0.75
    jer
    -0.69
    tale
    -0.69
    eding
    -0.66
     unveiling
    -0.65
    cision
    -0.64
     voiced
    -0.63
     effort
    -0.62
    POSITIVE LOGITS
     Schedule
    3.80
     Sched
    1.79
    Sche
    1.61
    dule
    1.40
     TBA
    1.19
     Stras
    1.19
     Regulations
    1.08
     Articles
    1.06
     Category
    1.03
     Controlled
    1.02
    Activations Density 0.017%

    No Known Activations