© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13247
    Prev
    Next
    INDEX
    Explanations

    Roman numerals, specifically the number "ii"

    oai_token-act-pair · gpt-3.5-turbo

    the Roman numeral representations of 'two' and 'three'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     galvan
    -0.75
     Sel
    -0.68
     staged
    -0.66
     Ing
    -0.65
     anchor
    -0.65
     Ramsey
    -0.64
     staging
    -0.63
     Stop
    -0.62
     unpre
    -0.61
     Rust
    -0.60
    POSITIVE LOGITS
    ii
    4.34
    iii
    3.13
     ii
    1.61
    II
    1.59
     iii
    1.45
    III
    1.39
    iae
    1.28
    iy
    1.27
    ius
    1.23
    i
    1.20
    Activations Density 0.014%

    No Known Activations