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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20118
    Prev
    Next
    INDEX
    Explanations

    online sources and technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to online news and media, particularly related to entertainment and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    range
    -0.74
    ventus
    -0.70
    drawn
    -0.68
    ardless
    -0.66
    optional
    -0.66
    weak
    -0.66
    actionDate
    -0.65
    gone
    -0.65
    Els
    -0.64
    adra
    -0.64
    POSITIVE LOGITS
     contributor
    1.17
     columnist
    1.17
     reporter
    1.15
     investigates
    1.15
     publishes
    1.09
     understands
    1.09
     readers
    1.08
     examines
    1.06
     reviewed
    1.02
     spoke
    1.02
    Activations Density 0.187%

    No Known Activations