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. 8-RES-JB
    6. 19204
    Prev
    Next
    INDEX
    Explanations

    terms related to qualities or characteristics of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    topics related to education and community-building activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    racuse
    -0.75
    oret
    -0.67
     Puzz
    -0.62
     typo
    -0.60
     saturation
    -0.60
     laure
    -0.59
     Ago
    -0.58
    icut
    -0.56
    odder
    -0.56
     pickups
    -0.55
    POSITIVE LOGITS
    .–
    0.72
    depending
    0.71
     alike
    0.70
     respectively
    0.70
    EMENT
    0.67
    etary
    0.66
    .</
    0.65
    -+-+
    0.64
    STEM
    0.64
     governed
    0.62
    Activations Density 0.557%

    No Known Activations