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. 0-RES-JB
    6. 796
    Prev
    Next
    INDEX
    Explanations

    numbers representing quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those in the 90s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    è£ħ
    -0.74
    inking
    -0.72
    ahime
    -0.66
    TAG
    -0.61
    TEXTURE
    -0.61
    taboola
    -0.60
    embed
    -0.60
    :{
    -0.60
    spir
    -0.60
    Ã
    -0.60
    POSITIVE LOGITS
     93
    2.78
     92
    2.78
     91
    2.67
     94
    2.66
     89
    2.47
     88
    2.41
     96
    2.41
     97
    2.37
     87
    2.30
     98
    2.30
    Activations Density 0.043%

    No Known Activations