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. 9-RES-JB
    6. 12958
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets containing specific syntax elements

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and error handling in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.78
     corrid
    -0.63
    rium
    -0.62
     Anglic
    -0.61
     Sabha
    -0.61
     Scandinavian
    -0.61
     Bul
    -0.61
     satirical
    -0.60
     Volvo
    -0.59
     Corridor
    -0.58
    POSITIVE LOGITS
     !
    1.19
    defined
    1.10
    ==
    1.06
    empty
    0.95
    true
    0.93
     ==
    0.92
    existing
    0.90
     !=
    0.90
     (!
    0.89
    instance
    0.87
    Activations Density 0.042%

    No Known Activations