© 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. 2-RES-JB
    11. 9023
    Prev
    Next
    INDEX
    Explanations

    Roman numerals followed by 'III'

    oai_token-act-pair · gpt-3.5-turbo

    references to the Roman numeral 'III'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pal
    -0.74
    arching
    -0.71
    ãĤ±
    -0.70
    poll
    -0.68
    bear
    -0.66
    feed
    -0.64
    organ
    -0.64
    staking
    -0.62
    д
    -0.62
    clock
    -0.61
    POSITIVE LOGITS
    III
    1.24
     III
    1.11
    II
    1.10
    rd
    0.95
    abba
    0.84
    omics
    0.79
    ratulations
    0.78
    ensical
    0.76
     IV
    0.76
    RD
    0.75
    Activations Density 0.009%

    No Known Activations