© 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. 10-RES-JB
    11. 20669
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgency or promptness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating urgency or the need for prompt action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uph
    -0.79
    âĵĺ
    -0.77
    gments
    -0.76
    oir
    -0.75
    tick
    -0.74
    sson
    -0.73
    ARS
    -0.70
    âĹ¼
    -0.69
    TOP
    -0.69
    gem
    -0.68
    POSITIVE LOGITS
     possible
    1.58
     practicable
    1.53
     feasible
    1.22
     Possible
    1.14
     feas
    1.04
     conceivable
    1.03
     imaginable
    0.96
     sunrise
    0.88
     dawn
    0.86
     reasonably
    0.83
    Activations Density 0.041%

    No Known Activations