© 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. 7-RES-JB
    11. 1849
    Prev
    Next
    INDEX
    Explanations

    phrases related to patience and impatience

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to patience and impatience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -1.11
    aucus
    -0.92
    tein
    -0.84
    unin
    -0.76
    orn
    -0.76
    roots
    -0.74
    lander
    -0.73
    ura
    -0.73
    ORN
    -0.71
    olesterol
    -0.70
    POSITIVE LOGITS
     patience
    1.22
     patiently
    1.10
     persever
    1.01
     delays
    0.74
     delay
    0.74
     endurance
    0.73
     pige
    0.73
     interval
    0.71
     impatient
    0.70
     gauge
    0.70
    Activations Density 0.030%

    No Known Activations