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. 4-RES-JB
    6. 5385
    Prev
    Next
    INDEX
    Explanations

    instances of the word "telephone"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the telephone and related communications technology

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

    No Comments

    Negative Logits
    reci
    -0.90
    ebook
    -0.81
     Ridley
    -0.76
    ded
    -0.74
    arent
    -0.71
    ais
    -0.71
    ean
    -0.71
    iverpool
    -0.70
    rake
    -0.69
    iesta
    -0.69
    POSITIVE LOGITS
     booths
    0.91
     Telephone
    0.91
     telephone
    0.90
     handset
    0.89
     hotline
    0.83
     booth
    0.82
    NetMessage
    0.81
     contacts
    0.81
     answ
    0.80
     communication
    0.79
    Activations Density 0.015%

    No Known Activations