© 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. 10116
    Prev
    Next
    INDEX
    Explanations

    references to obituaries

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ob", particularly in various contexts

    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
    lease
    -0.84
    cation
    -0.76
    manship
    -0.75
    ELS
    -0.74
    gage
    -0.70
    calling
    -0.70
    culture
    -0.69
     Cham
    -0.68
    illard
    -0.67
    resident
    -0.67
    POSITIVE LOGITS
     ob
    3.86
     Ob
    1.91
    Ob
    1.54
     OB
    1.36
     obe
    1.18
     unob
    1.12
     obs
    1.11
     circum
    1.03
    ob
    1.02
     disob
    1.01
    Activations Density 0.024%

    No Known Activations