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. 23392
    Prev
    Next
    INDEX
    Explanations

    technical terms related to relay operations and communication

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "relay" and its variations, indicating a focus on communication or transmission themes

    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
     Extrem
    -0.79
    arf
    -0.68
    ablishment
    -0.68
    eele
    -0.67
    argon
    -0.66
     Shank
    -0.66
    RAW
    -0.65
    isan
    -0.64
    ritis
    -0.63
    laus
    -0.63
    POSITIVE LOGITS
     relay
    1.39
     mosqu
    0.99
     relayed
    0.81
    oute
    0.75
    dayName
    0.73
    pole
    0.73
     announ
    0.73
     cooker
    0.69
     volley
    0.67
     messenger
    0.66
    Activations Density 0.003%

    No Known Activations