© 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. 4-RES-JB
    11. 12501
    Prev
    Next
    INDEX
    Explanations

    references to the term "dollar"

    oai_token-act-pair · gpt-3.5-turbo

    references to the dollar and its value in economic discussions

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

    No Comments

    Negative Logits
    ettings
    -0.83
    hern
    -0.73
    CRIP
    -0.73
    KEN
    -0.70
    udic
    -0.69
     Nare
    -0.68
     Aval
    -0.68
     Radiation
    -0.67
    CAST
    -0.66
    auldron
    -0.66
    POSITIVE LOGITS
     dollar
    1.10
    dollar
    0.93
    hyde
    0.87
     dollars
    0.87
     Dollar
    0.80
     sterling
    0.78
     ($)
    0.78
     fung
    0.74
    ollar
    0.73
     outl
    0.73
    Activations Density 0.013%

    No Known Activations