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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 14605
    Prev
    Next
    INDEX
    Explanations

    financial amounts or numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly in a context related to statistics or financial data

    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
     shopping
    -0.72
    ihad
    -0.69
     Tw
    -0.68
    sonian
    -0.66
     handwritten
    -0.65
    icial
    -0.65
     phenomen
    -0.64
     wo
    -0.63
     Po
    -0.61
     heart
    -0.60
    POSITIVE LOGITS
    686
    1.11
    685
    1.07
    606
    1.06
    604
    1.05
    806
    1.03
    803
    1.02
    017
    1.02
    657
    1.01
    304
    1.00
    807
    0.99
    Activations Density 0.047%

    No Known Activations