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. 0-RES-JB
    6. 731
    Prev
    Next
    INDEX
    Explanations

    names or terms related to positions of authority or distinction

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Emeritus" or similar honorary titles

    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
    venue
    -0.77
    BP
    -0.76
    Tank
    -0.69
     mph
    -0.65
     Pictures
    -0.64
    ban
    -0.64
    KO
    -0.64
    fp
    -0.62
    double
    -0.62
    aho
    -0.62
    POSITIVE LOGITS
     Emer
    4.14
     emer
    3.47
    Emer
    2.77
    emer
    1.47
     Emerald
    1.40
     Emerging
    1.15
     emergencies
    1.05
     Aure
    0.94
     Everett
    0.92
     Lauder
    0.91
    Activations Density 0.014%

    No Known Activations