© 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. 6-RES-JB
    11. 13547
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to computer hardware components

    oai_token-act-pair · gpt-3.5-turbo

    references to Intel processors and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.81
    vim
    -0.78
     Yelp
    -0.76
    mone
    -0.76
     Petr
    -0.74
     Shelter
    -0.74
    uscript
    -0.73
     Homeless
    -0.72
    ibli
    -0.70
     Lester
    -0.69
    POSITIVE LOGITS
     GPUs
    1.36
     CPUs
    1.35
     GPU
    1.26
     processors
    1.23
     chipset
    1.18
     cores
    1.12
     processor
    1.11
     architectures
    1.10
     CPU
    1.09
     GDDR
    1.08
    Activations Density 0.222%

    No Known Activations