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. 7-RES-JB
    6. 8062
    Prev
    Next
    INDEX
    Explanations

    phrases related to the financial institution "Citigroup."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company Citigroup or its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.92
     Chronicle
    -0.76
     4090
    -0.74
    ball
    -0.70
    âĢ¢âĢ¢
    -0.68
    ¿½
    -0.65
     Hots
    -0.65
     Butterfly
    -0.65
     Thumbnails
    -0.64
     Peninsula
    -0.63
    POSITIVE LOGITS
    ration
    0.96
    tered
    0.96
    ulous
    0.96
    ters
    0.92
    odied
    0.91
    igroup
    0.90
    rary
    0.90
    rate
    0.88
    rix
    0.87
    tering
    0.87
    Activations Density 0.058%

    No Known Activations