© 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 EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 1507
    Prev
    Next
    INDEX
    Explanations

    phrases related to urging or encouraging actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "urging."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Surv
    -0.82
     Flan
    -0.73
     Kinnikuman
    -0.72
    çĦ
    -0.69
    sung
    -0.66
    imb
    -0.63
     Highlander
    -0.63
     Sieg
    -0.63
    ppo
    -0.61
    ju
    -0.60
    POSITIVE LOGITS
     urging
    0.95
    irection
    0.86
    itudinal
    0.77
    tip
    0.76
     usher
    0.75
     incent
    0.75
    =]
    0.71
    redients
    0.69
     caution
    0.69
    OPLE
    0.69
    Activations Density 0.018%

    No Known Activations