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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 14253
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions, such as selling products or businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to selling and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iration
    -0.65
    Ùĩ
    -0.65
    verty
    -0.64
    ulhu
    -0.64
    orney
    -0.64
    cone
    -0.62
    Tip
    -0.62
     Dominican
    -0.62
    INO
    -0.60
    Parameter
    -0.58
    POSITIVE LOGITS
     commodities
    0.98
     commodity
    0.94
     cheaply
    0.91
     goods
    0.90
     tickets
    0.88
     groceries
    0.85
     auction
    0.84
     DVDs
    0.84
     surplus
    0.82
     coupons
    0.81
    Activations Density 0.149%

    No Known Activations