© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 4913
    Prev
    Next
    INDEX
    Explanations

    names and terms related to public relations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Relations" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finished
    -0.76
     finish
    -0.71
     smoke
    -0.71
     pad
    -0.70
     cough
    -0.69
     packed
    -0.68
     ma
    -0.68
     crowd
    -0.67
     blast
    -0.67
     hog
    -0.67
    POSITIVE LOGITS
     Relations
    4.13
    Relations
    2.68
    relations
    2.41
     Relationship
    1.98
     relations
    1.91
     relationships
    1.48
     Affairs
    1.47
     Friendship
    1.22
     Partners
    1.18
     relationship
    1.17
    Activations Density 0.012%

    No Known Activations