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. 0-RES-JB
    6. 21493
    Prev
    Next
    INDEX
    Explanations

    references to a specific telecommunication company named Verizon

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Verizon brand and its services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Helm
    -0.65
     recogn
    -0.64
     anthrop
    -0.63
     Num
    -0.63
    ife
    -0.62
    imb
    -0.62
     colour
    -0.62
     âĶ
    -0.62
    oly
    -0.61
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.61
    POSITIVE LOGITS
     Verizon
    3.68
     Sprint
    1.91
     Comcast
    1.87
     Motorola
    1.74
     Qualcomm
    1.62
    izon
    1.52
     LTE
    1.49
     Huawei
    1.42
     FedEx
    1.41
     AOL
    1.38
    Activations Density 0.011%

    No Known Activations