© 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. 16757
    Prev
    Next
    INDEX
    Explanations

    references to hardware specifications like storage, RAM, and memory cards within the text

    oai_token-act-pair · gpt-3.5-turbo

    specifications related to memory and storage in electronic devices

    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
    viol
    -0.74
    rians
    -0.72
    áµ
    -0.72
    sted
    -0.70
    bart
    -0.68
    iquette
    -0.67
    eness
    -0.67
    Sax
    -0.67
    cin
    -0.65
     Samar
    -0.65
    POSITIVE LOGITS
     storage
    1.09
     HDD
    1.07
     GDDR
    1.00
    VIDIA
    1.00
     PCIe
    0.96
     SSD
    0.96
     Storage
    0.93
    Storage
    0.93
     chipset
    0.91
     DDR
    0.90
    Activations Density 0.145%

    No Known Activations