© 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. 4278
    Prev
    Next
    INDEX
    Explanations

    keywords related to data manipulation and organization, such as filtering, searching, sorting, and grouping

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the methodology of categorization or grouping based on the word "by"

    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
    ivas
    -0.72
    SPONSORED
    -0.68
    los
    -0.67
    });
    -0.67
    bring
    -0.66
    ati
    -0.65
    upon
    -0.65
    inea
    -0.63
    ETF
    -0.63
    hya
    -0.63
    POSITIVE LOGITS
     virtue
    1.16
     clicking
    1.05
     selecting
    0.98
    laws
    0.95
     specifying
    0.92
     assigning
    0.91
     default
    0.90
     adding
    0.90
    products
    0.88
     multiplying
    0.85
    Activations Density 0.108%

    No Known Activations