© 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. 0-RES-JB
    11. 12127
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, particularly acid reflux

    oai_token-act-pair · gpt-3.5-turbo

    terms related to luxury and flexibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forgive
    -0.76
    seed
    -0.75
    itudinal
    -0.75
     recorder
    -0.75
    cknowled
    -0.72
     seeds
    -0.71
     seed
    -0.70
    iminary
    -0.69
     Anchorage
    -0.69
    arah
    -0.69
    POSITIVE LOGITS
    lux
    4.43
     Lux
    2.01
     lux
    1.84
    flex
    1.50
    plex
    1.48
     flux
    1.28
     flex
    1.18
    UX
    1.14
    ux
    1.11
     Flex
    1.04
    Activations Density 0.039%

    No Known Activations