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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4548
    Prev
    Next
    INDEX
    Explanations

    references to a company or service named "Starz Entertainment"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of entertainment companies and their associations

    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
    bage
    -0.81
     grop
    -0.80
    ebin
    -0.78
     trash
    -0.76
     queues
    -0.75
     skim
    -0.75
     snatch
    -0.74
     bothering
    -0.74
     fodder
    -0.74
     cuts
    -0.74
    POSITIVE LOGITS
     subsidiaries
    1.35
     LLC
    1.25
     headquartered
    1.25
    ®,
    1.19
    quartered
    1.18
     subsidiary
    1.16
     Company
    1.11
     Sponsor
    1.09
     Inc
    1.09
    ®
    1.07
    Activations Density 0.286%

    No Known Activations