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. 7-RES-JB
    6. 24274
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and project development

    oai_token-act-pair · gpt-3.5-turbo

    information related to experimental projects and their phases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hating
    -0.80
     sins
    -0.78
     hates
    -0.77
     traitor
    -0.76
    ghazi
    -0.76
     hated
    -0.75
     evils
    -0.74
    deen
    -0.72
    Terror
    -0.70
     hatred
    -0.67
    POSITIVE LOGITS
     workshops
    0.95
     rollout
    0.84
     prototypes
    0.82
     crowdfunding
    0.80
     collaborations
    0.79
     outreach
    0.79
     volunteers
    0.78
     partnerships
    0.75
     licences
    0.74
     Canary
    0.74
    Activations Density 1.073%

    No Known Activations