© 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. 3-RES-JB
    11. 10705
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgency or prompt action

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the urgency or necessity of doing things as soon as possible

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mare
    -0.93
    worn
    -0.84
    bane
    -0.83
    wa
    -0.83
    lua
    -0.82
    wu
    -0.81
    oute
    -0.77
    mar
    -0.76
    aw
    -0.76
    wr
    -0.75
    POSITIVE LOGITS
     srfAttach
    0.86
    isSpecialOrderable
    0.84
     conclud
    0.79
     embodiments
    0.75
     alternatives
    0.74
     indicators
    0.70
    acers
    0.70
     foreseeable
    0.69
    iary
    0.69
     feas
    0.68
    Activations Density 0.018%

    No Known Activations