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. 4-RES-JB
    6. 15078
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between different entities such as family, friends, and health

    oai_token-act-pair · gpt-3.5-turbo

    instances of gratitude or expressions of appreciation

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

    No Comments

    Negative Logits
    hig
    -0.74
    lycer
    -0.73
    ÅĤ
    -0.72
    vier
    -0.71
    uesday
    -0.71
    wire
    -0.71
    uter
    -0.70
    Tai
    -0.70
    nces
    -0.69
    uce
    -0.69
    POSITIVE LOGITS
     namesake
    0.75
     amen
    0.72
     counterparts
    0.71
     Sutherland
    0.70
     brethren
    0.69
     selves
    0.66
     neighbors
    0.66
     neigh
    0.64
     surroundings
    0.63
     successors
    0.62
    Activations Density 0.526%

    No Known Activations