© 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. 10-RES-JB
    11. 7243
    Prev
    Next
    INDEX
    Explanations

    dates and names related to legal cases or authorities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their professional roles or affiliations

    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
     Ajax
    -0.84
     Odyssey
    -0.81
     Arkham
    -0.74
     TBD
    -0.73
     Normandy
    -0.72
     Scotland
    -0.71
     Sixers
    -0.71
    brance
    -0.69
     Ukip
    -0.68
    Plugin
    -0.67
    POSITIVE LOGITS
     Zhou
    1.96
     Jiang
    1.96
     Zhang
    1.87
     Yuan
    1.87
     Tian
    1.85
     Qing
    1.84
     Zhu
    1.83
     Xu
    1.82
     Huang
    1.82
     Zhao
    1.81
    Activations Density 0.488%

    No Known Activations