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. 3-RES-JB
    6. 18942
    Prev
    Next
    INDEX
    Explanations

    Hebrew words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special or non-standard characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hedral
    -0.96
    zzi
    -0.79
    chy
    -0.79
    apon
    -0.79
    ufact
    -0.74
     Valentine
    -0.72
     Twist
    -0.71
    ille
    -0.70
     Print
    -0.69
    yip
    -0.69
    POSITIVE LOGITS
     ×
    1.13
    ÙĨ
    1.02
    Ļ
    0.95
    ×Ļ×
    0.90
    ׾
    0.90
    ×Ļ
    0.88
    ש
    0.87
    ķ
    0.85
    ŀ
    0.84
    ļ
    0.84
    Activations Density 0.011%

    No Known Activations