© 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. 7-RES-JB
    11. 8619
    Prev
    Next
    INDEX
    Explanations

    words related to payment or settling debts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pay."

    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
    bum
    -0.77
    ierre
    -0.72
    iber
    -0.68
    ogue
    -0.66
    olit
    -0.65
    Í
    -0.63
    aughs
    -0.63
    icity
    -0.62
    Aim
    -0.61
    âĸĪâĸĪâĸĪâĸĪ
    -0.61
    POSITIVE LOGITS
    checks
    1.02
     taxes
    0.96
     dividends
    0.96
     dues
    0.94
     royalties
    0.90
     debts
    0.87
     owed
    0.85
    outs
    0.83
     dearly
    0.83
    roll
    0.82
    Activations Density 0.045%

    No Known Activations