© 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. 4-RES-JB
    11. 14695
    Prev
    Next
    INDEX
    Explanations

    words related to computer operating systems, particularly focusing on the term "operating"

    oai_token-act-pair · gpt-3.5-turbo

    references to operating systems

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

    No Comments

    Negative Logits
    hon
    -0.86
    ildo
    -0.83
    oulder
    -0.77
    ļéĨĴ
    -0.77
    idential
    -0.77
    ohl
    -0.76
    chery
    -0.76
    igham
    -0.76
    annie
    -0.74
    hak
    -0.74
    POSITIVE LOGITS
     "$:/
    0.79
    ates
    0.75
     system
    0.71
     systems
    0.71
     reperto
    0.70
     distributions
    0.69
     theorem
    0.68
     architectures
    0.68
     platforms
    0.67
     emulator
    0.67
    Activations Density 0.014%

    No Known Activations