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. 21445
    Prev
    Next
    INDEX
    Explanations

    the word "aur" repeated in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or geographical terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     SO
    -0.69
     streaming
    -0.64
     stream
    -0.63
     Bottom
    -0.61
     Lo
    -0.61
     streamed
    -0.61
     tie
    -0.60
     hearts
    -0.60
     secession
    -0.60
     streams
    -0.60
    POSITIVE LOGITS
    aur
    4.64
    auri
    2.65
    aurus
    1.89
    aura
    1.70
    au
    1.14
    urion
    1.14
     Saur
    1.07
     Aur
    1.05
    urus
    1.00
    aul
    0.97
    Activations Density 0.011%

    No Known Activations