© 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. 8-RES-JB
    11. 20295
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to displays in electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of displays in technology products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sted
    -0.87
    estern
    -0.86
    ESE
    -0.79
    istani
    -0.77
    doms
    -0.77
    glers
    -0.76
    anthrop
    -0.76
    ghan
    -0.74
    ozy
    -0.72
    bard
    -0.71
    POSITIVE LOGITS
     brightness
    1.05
     OLED
    0.99
     TVs
    0.98
     LCD
    0.98
     MacBook
    0.96
     sockets
    0.95
    Pixel
    0.93
     adapter
    0.91
    tops
    0.87
     touchscreen
    0.87
    Activations Density 0.055%

    No Known Activations