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. 10-RES-JB
    6. 19451
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to communication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arte
    -0.78
    watch
    -0.74
    lah
    -0.72
    uries
    -0.71
    é¾įå
    -0.69
    stad
    -0.68
    uck
    -0.68
    udo
    -0.67
    ournament
    -0.66
    wing
    -0.65
    POSITIVE LOGITS
     orally
    1.05
     verbally
    1.01
     via
    1.00
     messages
    0.97
     communication
    0.94
     signals
    0.90
     communicate
    0.87
     communicating
    0.85
     communicates
    0.84
     electronically
    0.83
    Activations Density 0.058%

    No Known Activations