Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4182
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    references to Roman numerals, particularly 'III', 'II', 'VII', and 'IV'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boards
    -0.95
    board
    -0.79
    places
    -0.78
    lins
    -0.77
    rules
    -0.76
    feed
    -0.75
    chant
    -0.74
    faced
    -0.74
    д
    -0.73
    sters
    -0.72
    POSITIVE LOGITS
    III
    1.16
    II
    1.05
    FY
    0.77
    ATA
    0.77
    IV
    0.73
    IC
    0.70
    ACA
    0.69
     Centauri
    0.69
    HF
    0.69
     III
    0.69
    Activations Density 0.030%

    No Known Activations