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

    Neuronpedia

    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. 8-RES-JB
    11. 20483
    Prev
    Next
    INDEX
    Explanations

    brands and models related to computer hardware, particularly graphics cards

    oai_token-act-pair · gpt-3.5-turbo

    references to specific graphics card models and their specifications

    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
    glers
    -0.81
    obos
    -0.76
    esty
    -0.73
    worthy
    -0.72
    cott
    -0.69
    mone
    -0.69
     bowel
    -0.67
    email
    -0.67
     Marilyn
    -0.67
    zynski
    -0.67
    POSITIVE LOGITS
     GPUs
    1.24
    PDATE
    1.14
    GPU
    1.11
     GPU
    1.09
     GTX
    1.09
     Nvidia
    1.06
     GeForce
    1.03
     Quadro
    1.02
    vidia
    1.00
     SLI
    0.93
    Activations Density 0.093%

    No Known Activations