Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12447
    Prev
    Next
    INDEX
    Explanations

    technical instructions and troubleshooting information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technological actions and responses

    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
     Reconstruction
    -0.81
     Canaver
    -0.72
     Historically
    -0.68
     Anthropology
    -0.67
     McDonnell
    -0.67
     Nau
    -0.63
     historian
    -0.63
     Sturgeon
    -0.62
     Robertson
    -0.61
     Lyndon
    -0.61
    POSITIVE LOGITS
     anymore
    0.79
     distractions
    0.79
     notifications
    0.75
     noises
    0.72
     ones
    0.71
     ;)
    0.71
     attachments
    0.70
     tabs
    0.70
     clicks
    0.68
     adjustments
    0.68
    Activations Density 0.911%

    No Known Activations