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. 1-RES-JB
    6. 5921
    Prev
    Next
    INDEX
    Explanations

    Unicode characters

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols, particularly those related to non-Latin scripts or special formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accord
    -0.71
     sleeves
    -0.69
     strongest
    -0.68
     fragmented
    -0.68
     stri
    -0.68
     Accord
    -0.67
    raints
    -0.67
     strengths
    -0.67
     draped
    -0.67
    esville
    -0.67
    POSITIVE LOGITS
    IJ
    1.45
    ×Ļ×
    1.02
    ׾
    1.02
    ×ķ
    1.01
    ת
    0.99
    ï¸ı
    0.99
    κ
    0.98
    é¾
    0.95
    Ĺ
    0.95
    µ
    0.95
    Activations Density 0.004%

    No Known Activations