© 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 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. 9-RES-JB
    11. 2272
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the concept of time, effort, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the amount of time required for various actions or tasks

    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
    vec
    -0.85
    ailability
    -0.78
    Associated
    -0.76
    ociated
    -0.73
    Ü
    -0.72
    æ©Ł
    -0.71
    Enabled
    -0.70
    ¥µ
    -0.70
    urden
    -0.69
    arding
    -0.67
    POSITIVE LOGITS
     convincing
    0.82
     concerted
    0.81
     courage
    0.77
     persuasion
    0.70
     breaths
    0.68
     patience
    0.68
     awhile
    0.68
     ingenuity
    0.67
     persu
    0.67
     milliseconds
    0.66
    Activations Density 0.087%

    No Known Activations