© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12280
    Prev
    Next
    INDEX
    Explanations

    news outlets and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to various news outlets and media organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bonding
    -0.82
     leveling
    -0.77
     balancing
    -0.72
     females
    -0.70
     males
    -0.69
    locks
    -0.68
     conditioning
    -0.68
    beard
    -0.68
     awoken
    -0.68
     bonded
    -0.68
    POSITIVE LOGITS
     Huffington
    1.36
     Newsweek
    1.33
     NYT
    1.23
     Politico
    1.23
     Daily
    1.22
     MSNBC
    1.22
     CNN
    1.22
     Observer
    1.19
     Univ
    1.18
     CNBC
    1.18
    Activations Density 0.133%

    No Known Activations