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. 1-RES-JB
    6. 8113
    Prev
    Next
    INDEX
    Explanations

    words related to communication and interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of communication in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jury
    -0.77
    coat
    -0.74
    amina
    -0.74
    980
    -0.71
    035
    -0.70
    440
    -0.70
    155
    -0.70
    este
    -0.68
     Devils
    -0.68
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.68
    POSITIVE LOGITS
     communication
    1.19
     transmissions
    0.97
     Communication
    0.96
     communications
    0.95
    yip
    0.95
     communicates
    0.88
     protocols
    0.86
     behavi
    0.85
    communication
    0.83
     signals
    0.81
    Activations Density 0.006%

    No Known Activations