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. 21754
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly emphasizing a character named Morales

    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
     sled
    -0.73
     BT
    -0.72
     peac
    -0.71
     Kitty
    -0.70
     Nato
    -0.69
    Britain
    -0.68
    ilk
    -0.68
     autumn
    -0.67
    drawn
    -0.66
    âĹ¼
    -0.65
    POSITIVE LOGITS
     Morales
    2.61
     Guerrero
    2.59
     Ramirez
    2.41
     Gonzalez
    2.38
     Herrera
    2.37
     Ramos
    2.35
     Sanchez
    2.32
     Ortiz
    2.31
     Reyes
    2.30
     Hernandez
    2.30
    Activations Density 0.069%

    No Known Activations