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. 23472
    Prev
    Next
    INDEX
    Explanations

    company names in the entertainment industry

    oai_token-act-pair · gpt-3.5-turbo

    information related to entertainment companies and their services

    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
     anyway
    -0.86
     fodder
    -0.82
    ebin
    -0.79
     mock
    -0.75
    rez
    -0.74
     skim
    -0.74
     anyways
    -0.73
     leftover
    -0.73
     grop
    -0.72
     spoilers
    -0.72
    POSITIVE LOGITS
     headquartered
    1.20
    ®,
    1.09
    quartered
    1.08
    ablished
    1.02
    NYSE
    0.99
     Fortune
    0.98
     Serving
    0.97
     recognized
    0.96
    ®
    0.94
     subsidiaries
    0.94
    Activations Density 0.402%

    No Known Activations