© 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. 10-RES-JB
    11. 12872
    Prev
    Next
    INDEX
    Explanations

    the word "laptop"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of laptops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tale
    -0.88
    Relations
    -0.76
     Cosponsors
    -0.75
    κ
    -0.70
    ahn
    -0.67
    steen
    -0.67
    abiding
    -0.66
    reek
    -0.66
    ãĤ©
    -0.66
    relations
    -0.64
    POSITIVE LOGITS
     laptop
    1.09
    aptop
    1.07
     laptops
    1.07
     computers
    0.96
     MacBook
    0.93
     PCs
    0.90
     charger
    0.87
    pad
    0.87
     computer
    0.87
     CPUs
    0.86
    Activations Density 0.030%

    No Known Activations