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. 1-RES-JB
    6. 19053
    Prev
    Next
    INDEX
    Explanations

    words related to a specific topic or entity, in this case, "Panda."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "anda," indicating a focus on names or references related to "Anda," such as locations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sed
    -0.81
    kens
    -0.67
    kes
    -0.65
    PC
    -0.64
     mileage
    -0.64
    spect
    -0.63
    ny
    -0.63
     Rack
    -0.61
     Grind
    -0.61
    icka
    -0.60
    POSITIVE LOGITS
    emonium
    1.33
    anda
    0.96
    wana
    0.87
    heon
    0.82
    ahar
    0.80
    ibo
    0.79
    onda
    0.79
    arov
    0.78
     Haram
    0.78
    ani
    0.77
    Activations Density 0.006%

    No Known Activations