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. 9932
    Prev
    Next
    INDEX
    Explanations

    words related to journalists

    oai_token-act-pair · gpt-3.5-turbo

    mentions of journalists and issues related to their treatment or conditions

    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
    ensions
    -0.76
    BuyableInstoreAndOnline
    -0.74
    oku
    -0.72
    ergy
    -0.71
    xual
    -0.70
    inence
    -0.69
     Spa
    -0.67
    plan
    -0.66
    ranged
    -0.65
    ayne
    -0.64
    POSITIVE LOGITS
     Journalists
    1.03
     journalists
    1.03
     journalist
    0.87
     reporters
    0.81
     corps
    0.80
    Journal
    0.77
     photographers
    0.76
     laureate
    0.76
     covering
    0.75
    orters
    0.74
    Activations Density 0.029%

    No Known Activations