© 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. 1-RES-JB
    11. 16901
    Prev
    Next
    INDEX
    Explanations

    phrases related to large amounts or significant levels of something

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating significant quantities or amounts

    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
     livest
    -0.75
    relations
    -0.73
     Reincarn
    -0.70
     Siber
    -0.68
    minist
    -0.65
    agents
    -0.64
     Contin
    -0.64
    iche
    -0.64
    sim
    -0.64
    istar
    -0.63
    POSITIVE LOGITS
     hefty
    1.11
     chunk
    0.93
     bucks
    0.82
     notch
    0.77
    bilt
    0.77
     pric
    0.74
     tracts
    0.70
     whopping
    0.70
    uador
    0.70
     dow
    0.69
    Activations Density 0.023%

    No Known Activations