© 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. 434
    Prev
    Next
    INDEX
    Explanations

    phrases related to automation and automated processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to automation and automated processes

    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
    dn
    -0.90
    ings
    -0.80
    adr
    -0.78
    hoff
    -0.77
    hov
    -0.77
    rug
    -0.77
    nen
    -0.77
    mond
    -0.77
    marks
    -0.75
    nah
    -0.75
    POSITIVE LOGITS
     automated
    1.08
     automation
    0.98
     captcha
    0.96
     automate
    0.94
     autom
    0.92
     braking
    0.88
     systems
    0.83
     guiActiveUn
    0.79
     monitoring
    0.77
     scheduling
    0.77
    Activations Density 0.011%

    No Known Activations