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. 10710
    Prev
    Next
    INDEX
    Explanations

    numbers representing quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 30

    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
    à©
    -0.71
    channelAvailability
    -0.67
    anca
    -0.66
    SPONSORED
    -0.60
    iths
    -0.60
    èª
    -0.60
     fundament
    -0.59
    atz
    -0.59
    trump
    -0.58
    iac
    -0.56
    POSITIVE LOGITS
     30
    2.88
     40
    2.13
     25
    2.13
     29
    2.11
     60
    2.10
     20
    2.07
     31
    2.06
     28
    2.05
     35
    2.05
     45
    1.93
    Activations Density 0.023%

    No Known Activations