© 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. 4-RES-JB
    11. 9595
    Prev
    Next
    INDEX
    Explanations

    mentions of specific brands and products, particularly in the tech industry

    oai_token-act-pair · gpt-3.5-turbo

    specific product names and technologies related to consumer electronics

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

    No Comments

    Negative Logits
    steen
    -0.75
     bapt
    -0.73
    #$#$
    -0.73
    orkshire
    -0.71
    redited
    -0.70
     âĵĺ
    -0.68
    sted
    -0.67
    licts
    -0.67
     Petr
    -0.66
     è£ıè¦ļéĨĴ
    -0.65
    POSITIVE LOGITS
     chipset
    1.00
    USB
    0.99
     ASUS
    0.96
     accessories
    0.91
     handset
    0.89
     Acer
    0.88
     Accessories
    0.88
     Razer
    0.86
     MacBook
    0.86
     Asus
    0.86
    Activations Density 0.222%

    No Known Activations