© 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. 4-RES-JB
    11. 2280
    Prev
    Next
    INDEX
    Explanations

    medical conditions, anatomical terms, and scientific references

    oai_token-act-pair · gpt-3.5-turbo

    parentheses or references to supplementary information

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

    No Comments

    Negative Logits
     Lumpur
    -0.79
    quished
    -0.75
     lull
    -0.68
     millenn
    -0.67
     icy
    -0.67
    ottest
    -0.66
    amily
    -0.64
    ulhu
    -0.64
     nightly
    -0.62
     cryst
    -0.61
    POSITIVE LOGITS
    see
    1.44
    sic
    1.32
    including
    1.30
    emphasis
    1.25
    Figure
    1.17
    possibly
    1.17
    excluding
    1.17
    both
    1.16
    perhaps
    1.15
    although
    1.14
    Activations Density 0.179%

    No Known Activations