© 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. 23526
    Prev
    Next
    INDEX
    Explanations

    terms related to financial savings

    oai_token-act-pair · gpt-3.5-turbo

    references to financial savings

    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
    Else
    -0.78
    SOURCE
    -0.75
    ña
    -0.70
    ¯
    -0.68
     Hug
    -0.65
    HEAD
    -0.65
    Edited
    -0.65
    SPONSORED
    -0.64
     acidic
    -0.63
    ¯¯
    -0.63
    POSITIVE LOGITS
     savings
    1.28
     Savings
    1.25
    ilitarian
    0.85
    avorite
    0.83
     deposit
    0.80
     Saving
    0.79
    benefit
    0.76
     deposits
    0.73
    itures
    0.72
     Accounts
    0.71
    Activations Density 0.005%

    No Known Activations