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. 6-RES-JB
    6. 6116
    Prev
    Next
    INDEX
    Explanations

    language related to commentary, analysis, or criticism

    oai_token-act-pair · gpt-3.5-turbo

    elements related to themes of community and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amiya
    -0.54
    owder
    -0.52
    AMY
    -0.51
    air
    -0.51
    inguished
    -0.50
    aughters
    -0.49
    chant
    -0.49
    ittee
    -0.48
    oche
    -0.48
    chel
    -0.48
    POSITIVE LOGITS
     oneself
    0.88
     outweigh
    0.67
     blindly
    0.65
     disparate
    0.65
     equals
    0.63
     yourself
    0.62
     ourselves
    0.62
    ystem
    0.58
     evolves
    0.58
     solves
    0.57
    Activations Density 1.428%

    No Known Activations