© 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. 1-RES-JB
    11. 3793
    Prev
    Next
    INDEX
    Explanations

    words related to using a standardized structure or format as a basis for creating or understanding something

    oai_token-act-pair · gpt-3.5-turbo

    references to templates or structured formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ells
    -0.83
    obbies
    -0.76
    iqueness
    -0.73
    better
    -0.73
    azar
    -0.73
    skirts
    -0.73
     Gunn
    -0.70
    bringing
    -0.70
    acia
    -0.68
    Downloadha
    -0.66
    POSITIVE LOGITS
     template
    1.35
     Template
    1.17
     templates
    1.11
    plates
    1.07
    template
    0.94
     flare
    0.78
     outline
    0.77
     cout
    0.76
     blueprint
    0.76
     layout
    0.75
    Activations Density 0.004%

    No Known Activations