© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 17564
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions being made or involving payment

    oai_token-act-pair · gpt-3.5-turbo

    references to financial compensation or payments received

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ierre
    -0.80
     Scotia
    -0.77
    ãĥŁ
    -0.76
    _>
    -0.76
    ----------
    -0.74
    -----
    -0.72
    ember
    -0.72
    ãĤ¦
    -0.71
    âĸĪâĸĪâĸĪâĸĪ
    -0.70
    Cola
    -0.69
    POSITIVE LOGITS
     paid
    1.09
    paying
    0.95
     Paid
    0.91
     paying
    0.90
    paid
    0.89
    ħĭ
    0.88
     footing
    0.84
    outs
    0.81
    loads
    0.80
     subscribers
    0.80
    Activations Density 0.012%

    No Known Activations