Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22782
    Prev
    Next
    INDEX
    Explanations

    words related to psychological or emotional development and relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to development and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.78
    Joined
    -0.75
    ģĸ
    -0.70
     rightfully
    -0.70
    autions
    -0.66
     sender
    -0.66
     Mehran
    -0.65
     Macy
    -0.64
    elected
    -0.63
    aunting
    -0.62
    POSITIVE LOGITS
     skills
    0.77
     techniques
    0.73
    enegger
    0.73
     breakthrough
    0.73
     VK
    0.71
     technique
    0.71
     strategy
    0.71
     traction
    0.70
     technologies
    0.70
     trajectory
    0.70
    Activations Density 0.218%

    No Known Activations