Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11554
    Prev
    Next
    INDEX
    Explanations

    mentions of financial terms or concepts specifically related to balance sheets

    oai_token-act-pair · gpt-3.5-turbo

    references to financial balances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hood
    -0.72
    CHAT
    -0.69
    OLOG
    -0.69
    iatric
    -0.69
     ABE
    -0.68
    Haunted
    -0.65
    Bir
    -0.62
    PLIC
    -0.62
    selves
    -0.62
     Cosponsors
    -0.61
    POSITIVE LOGITS
     balance
    1.02
    balance
    0.96
     imbalance
    0.96
     balances
    0.91
    aments
    0.89
    balanced
    0.87
     sheet
    0.83
    amental
    0.80
    ament
    0.80
     balancing
    0.78
    Activations Density 0.010%

    No Known Activations