© 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. 7-RES-JB
    11. 12523
    Prev
    Next
    INDEX
    Explanations

    terms related to the Blue Angels, such as their name and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Blue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.85
    ROR
    -0.79
    NRS
    -0.78
    rolet
    -0.77
    uador
    -0.76
    ITNESS
    -0.75
    itates
    -0.74
    orship
    -0.72
    ernandez
    -0.71
    ETF
    -0.71
    POSITIVE LOGITS
    prints
    1.34
    grass
    1.30
    berry
    1.21
    bird
    1.03
    beard
    1.01
    berries
    0.98
     ribbon
    0.88
     Ribbon
    0.88
    heart
    0.88
    fin
    0.86
    Activations Density 0.023%

    No Known Activations