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. 7909
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to quiet or secretive communication, specifically whispers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quiet or secretive communication

    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
    unes
    -0.85
    ouf
    -0.77
    onut
    -0.74
    ATES
    -0.74
    arcity
    -0.72
    ordan
    -0.71
    rob
    -0.70
    aepernick
    -0.68
    ais
    -0.67
    Jer
    -0.67
    POSITIVE LOGITS
     whisper
    1.42
     whispers
    1.25
     whispering
    1.17
     aloud
    0.96
     whispered
    0.96
     louder
    0.83
     rumours
    0.82
     murm
    0.79
    tale
    0.78
     rumors
    0.76
    Activations Density 0.011%

    No Known Activations