© 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. 4-RES-JB
    11. 12481
    Prev
    Next
    INDEX
    Explanations

    Roman numerals, with a particular focus on the numeral "II" and "III"

    oai_token-act-pair · gpt-3.5-turbo

    references to various 'II' categories or designations

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

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.82
    ãĥ¼ãĥĨ
    -0.81
    boards
    -0.76
    notes
    -0.76
    д
    -0.75
    ãĤ§
    -0.75
    acters
    -0.73
    reens
    -0.70
    Tile
    -0.70
    tackle
    -0.69
    POSITIVE LOGITS
    II
    0.99
    HF
    0.98
    III
    0.92
    FY
    0.85
    nd
    0.76
    HS
    0.75
     Britann
    0.72
    ATA
    0.70
    ND
    0.69
    BM
    0.69
    Activations Density 0.012%

    No Known Activations