© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10325
    Prev
    Next
    INDEX
    Explanations

    uncommon or unusual occurrences

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "Odd" and related variations in context

    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
     serv
    -0.72
     soak
    -0.71
     immersion
    -0.68
     cascade
    -0.66
     citizenship
    -0.65
    REP
    -0.64
    burst
    -0.64
    article
    -0.63
    alone
    -0.63
     cu
    -0.62
    POSITIVE LOGITS
     Odd
    3.76
     Weird
    1.11
     Lucky
    1.07
    ocular
    1.01
    azard
    0.95
    dds
    0.93
     Pred
    0.93
     Strange
    0.93
     Osw
    0.92
     Gol
    0.91
    Activations Density 0.015%

    No Known Activations