© 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. 1-RES-JB
    11. 3779
    Prev
    Next
    INDEX
    Explanations

    references to specific models of graphics cards

    oai_token-act-pair · gpt-3.5-turbo

    references to specific graphics card models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Debor
    -0.75
    chy
    -0.70
     orally
    -0.67
    alties
    -0.63
    nel
    -0.63
    icative
    -0.62
    biz
    -0.62
    alez
    -0.61
     Petr
    -0.61
    igree
    -0.61
    POSITIVE LOGITS
     GTX
    1.18
    PDATE
    0.94
     SLI
    0.89
     GPUs
    0.84
     Quadro
    0.81
     GeForce
    0.79
    GPU
    0.75
    heed
    0.75
     lapt
    0.74
    eli
    0.71
    Activations Density 0.006%

    No Known Activations