© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2266
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or inevitability

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the necessity of taking action or making decisions in challenging situations

    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
     ASAP
    -0.87
     tomorrow
    -0.78
    udeb
    -0.76
    soon
    -0.71
     hereafter
    -0.71
    currently
    -0.70
     presently
    -0.69
    today
    -0.69
     Module
    -0.68
     antioxid
    -0.66
    POSITIVE LOGITS
     downright
    1.00
     mistaken
    0.99
     unintentionally
    0.98
     inadvertently
    0.97
     surprises
    0.96
     mistakenly
    0.93
     incorrectly
    0.93
     overlooked
    0.93
     accidentally
    0.93
     inadvert
    0.91
    Activations Density 0.315%

    No Known Activations