© 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. 8-RES-JB
    11. 2532
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presentation or laying out of ideas, proposals, or strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe presenting or laying out information or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ni
    -0.68
    inos
    -0.68
     luck
    -0.65
    ãĥĺ
    -0.64
    WT
    -0.63
     Advertisement
    -0.63
    avery
    -0.62
     [+
    -0.61
     CLSID
    -0.60
    nee
    -0.60
    POSITIVE LOGITS
     outlines
    1.18
     principles
    1.08
     plans
    0.99
     outline
    0.99
     strategies
    0.94
     goals
    0.92
     criteria
    0.91
     guidelines
    0.90
     Principles
    0.86
     how
    0.83
    Activations Density 0.121%

    No Known Activations