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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14434
    Prev
    Next
    INDEX
    Explanations

    specific entities and concepts related to various fields such as medical, economics, biology, politics, and journalism

    oai_token-act-pair · gpt-3.5-turbo

    specific names and organizations relevant to political or scientific contexts

    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
    •ans
    #5 activation: 8.68

    No Comments

    Negative Logits
     destro
    -0.59
    nesday
    -0.54
    ,...
    -0.54
    enegger
    -0.53
     prest
    -0.51
     beforehand
    -0.51
    sic
    -0.50
    *.
    -0.50
    terday
    -0.50
    jri
    -0.49
    POSITIVE LOGITS
    ¢
    0.56
    £
    0.56
    ®
    0.55
    ĩ
    0.55
    º
    0.54
    ł
    0.53
     Archive
    0.52
     Profile
    0.51
     âĢº
    0.50
    ©
    0.50
    Activations Density 0.678%

    No Known Activations