© 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. 10372
    Prev
    Next
    INDEX
    Explanations

    references to structured arrangement or organization involving rows or columns

    oai_token-act-pair · gpt-3.5-turbo

    references to rows and columns in a structured context, likely related to data tables or database queries

    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
    credit
    -0.76
    Rocket
    -0.76
    CTV
    -0.75
    estone
    -0.75
    Shell
    -0.75
    mint
    -0.74
    Merit
    -0.67
    zie
    -0.66
    Proof
    -0.65
    gan
    -0.63
    POSITIVE LOGITS
     rows
    1.29
     columns
    0.84
    arnaev
    0.83
    rows
    0.81
    hower
    0.76
    poons
    0.73
     SELECT
    0.73
    paces
    0.72
    urches
    0.71
    pread
    0.70
    Activations Density 0.028%

    No Known Activations