© 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. 20489
    Prev
    Next
    INDEX
    Explanations

    phrases that represent the epitome or exemplar of certain concepts, often in a contrasting or comparative manner

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "epitome" and its variations

    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
    interrupted
    -0.67
    Lago
    -0.65
     Worldwide
    -0.64
    ITED
    -0.63
     Safari
    -0.63
     independently
    -0.62
    CDC
    -0.61
     Bucks
    -0.61
    BSD
    -0.59
     cooperative
    -0.59
    POSITIVE LOGITS
    hetical
    1.20
    hetically
    1.19
    hesis
    1.09
    hetic
    1.04
    viation
    1.04
    helial
    1.03
    utor
    0.98
    ophone
    0.98
    ograph
    0.95
    ome
    0.95
    Activations Density 0.030%

    No Known Activations