© 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. 6-RES-JB
    11. 20459
    Prev
    Next
    INDEX
    Explanations

    keywords related to user interface elements and customization options

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to software and user interface elements

    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
    fund
    -0.77
    IVERS
    -0.76
    bred
    -0.74
    istani
    -0.74
    anol
    -0.74
    racuse
    -0.73
    vacc
    -0.72
    breeding
    -0.71
    ushima
    -0.68
    é¾įå
    -0.68
    POSITIVE LOGITS
     widget
    1.06
     toolbar
    1.05
     pane
    1.05
     popup
    1.05
     scrolling
    1.04
     sidebar
    0.98
     widgets
    0.97
     layout
    0.95
     interface
    0.91
     cursor
    0.91
    Activations Density 0.167%

    No Known Activations