© 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. 4-RES-JB
    11. 2807
    Prev
    Next
    INDEX
    Explanations

    scientific terms or references

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of science

    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
     Seasons
    -0.73
    âĢ¢âĢ¢
    -0.73
    leased
    -0.69
    ometown
    -0.68
    doms
    -0.67
    terior
    -0.65
    pora
    -0.64
     Shades
    -0.62
    ividual
    -0.62
    zik
    -0.61
    POSITIVE LOGITS
     fiction
    1.25
     Fiction
    1.11
     science
    0.85
    science
    0.83
    craft
    0.82
    istry
    0.81
    icist
    0.81
    fiction
    0.81
     literacy
    0.80
    uality
    0.80
    Activations Density 0.023%

    No Known Activations