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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 340
    Prev
    Next
    INDEX
    Explanations

    information related to data sources or references

    oai_token-act-pair · gpt-3.5-turbo

    references to sources and citations within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kidd
    -0.97
     MON
    -0.90
    292
    -0.85
     maneu
    -0.85
    emon
    -0.83
    Mont
    -0.82
     292
    -0.82
     Chou
    -0.81
     Monroe
    -0.80
     lou
    -0.80
    POSITIVE LOGITS
    source
    1.31
    SOURCE
    1.18
    Source
    1.14
     Source
    1.09
    src
    1.06
     source
    1.06
     sourcing
    0.95
    ource
    0.94
     sources
    0.91
    ources
    0.87
    Activations Density 0.308%

    No Known Activations