© 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. 8-RES-JB
    11. 6324
    Prev
    Next
    INDEX
    Explanations

    instances where a situation is being described as different from what is expected

    oai_token-act-pair · gpt-3.5-turbo

    the word "Instead" and its various forms as a pivot in discussions or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AZ
    -0.67
    Condition
    -0.61
    rament
    -0.59
     neighbourhood
    -0.59
    ENTS
    -0.58
    ental
    -0.57
    SF
    -0.57
    ties
    -0.56
    gin
    -0.55
    emate
    -0.55
    POSITIVE LOGITS
     opting
    0.78
    ples
    0.75
    terness
    0.75
    ertodd
    0.70
    ortun
    0.69
    chart
    0.66
    ilon
    0.65
    zbek
    0.65
    ¬¼
    0.65
     preferring
    0.62
    Activations Density 0.024%

    No Known Activations