© 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. 7652
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large quantity or extent of something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "great" in various contexts, indicating emphasis or significant quantity

    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
    clips
    -0.84
    meta
    -0.68
    VR
    -0.67
    mitt
    -0.64
    graded
    -0.62
    qqa
    -0.61
    ©¶æ
    -0.61
    FML
    -0.61
     Eval
    -0.60
    KA
    -0.59
    POSITIVE LOGITS
    sword
    1.18
     deal
    1.04
     strides
    1.01
    axe
    0.93
     lengths
    0.90
     distances
    0.89
     accomplishment
    0.89
     outdoors
    0.87
     irony
    0.86
     enthus
    0.84
    Activations Density 0.062%

    No Known Activations