© 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. 10-RES-JB
    11. 13657
    Prev
    Next
    INDEX
    Explanations

    phrases related to different types of technology and arts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to peer-to-peer systems and transactions

    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
     Canaver
    -0.69
     aback
    -0.58
    pmwiki
    -0.58
    DragonMagazine
    -0.56
     quotations
    -0.55
     predictions
    -0.53
     Gutenberg
    -0.53
     misconceptions
    -0.51
     explanations
    -0.51
     tactics
    -0.51
    POSITIVE LOGITS
    )).
    0.71
    )."
    0.65
    %).
    0.60
    ))))
    0.58
    tops
    0.57
    Ń·
    0.57
    "))
    0.56
    ¹
    0.56
    ometown
    0.55
    azo
    0.54
    Activations Density 0.773%

    No Known Activations