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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 8424
    Prev
    Next
    INDEX
    Explanations

    specific references or acronyms related to a particular subject, possibly related to a university or organization using the abbreviation "SU."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of vehicle or organizational entity, particularly related to SUVs and various subscription units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lyme
    -0.73
    wright
    -0.69
     Ferdinand
    -0.67
     Turks
    -0.67
    working
    -0.66
    abouts
    -0.64
    ograms
    -0.63
    arta
    -0.63
     orders
    -0.62
    flies
    -0.62
    POSITIVE LOGITS
    SU
    1.13
    FFER
    1.01
    pper
    0.93
    gur
    0.92
    arez
    0.92
    pta
    0.88
    ITS
    0.86
    pling
    0.86
    JO
    0.86
    pped
    0.85
    Activations Density 0.005%

    No Known Activations