© 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. 6-RES-JB
    11. 10723
    Prev
    Next
    INDEX
    Explanations

    instances of ordinal numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "second" and other ordinal indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.75
    gravity
    -0.67
    auna
    -0.66
    doms
    -0.66
    Tokens
    -0.65
    aucus
    -0.64
    aba
    -0.64
    values
    -0.64
    tests
    -0.62
    matter
    -0.62
    POSITIVE LOGITS
     consecutive
    1.08
     successive
    0.79
     anniversary
    0.67
     reigning
    0.65
     holiest
    0.65
     prominent
    0.65
     installment
    0.64
    NetMessage
    0.64
     longest
    0.64
     nationally
    0.64
    Activations Density 0.086%

    No Known Activations