© 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. 11-RES-JB
    11. 8322
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remain" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remain" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.83
    ramid
    -0.82
    PsyNetMessage
    -0.75
    esity
    -0.74
    oday
    -0.73
    osp
    -0.72
    ongyang
    -0.72
    ologies
    -0.71
    ough
    -0.70
    idth
    -0.69
    POSITIVE LOGITS
     silent
    1.15
     steadfast
    1.11
     anonymous
    1.05
     unchanged
    0.99
     mum
    0.99
     loyal
    0.99
     vigilant
    0.95
     unnamed
    0.95
     adamant
    0.94
     faithful
    0.90
    Activations Density 0.063%

    No Known Activations