Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2478
    Prev
    Next
    INDEX
    Explanations

    scientific journal article references

    oai_token-act-pair · gpt-3.5-turbo

    references to scholarly publications and journal articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tsky
    -0.83
     swast
    -0.77
    ardless
    -0.73
    chwitz
    -0.73
     burner
    -0.72
    roo
    -0.72
     candles
    -0.69
     furn
    -0.69
    chio
    -0.68
     ceilings
    -0.67
    POSITIVE LOGITS
     Pediatrics
    1.14
     Neuroscience
    1.03
    Phys
    0.99
     Proceedings
    0.97
     Biology
    0.96
     Perspect
    0.95
     Biol
    0.95
     PLoS
    0.93
     Psychiatry
    0.93
     Journal
    0.92
    Activations Density 0.130%

    No Known Activations