© 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. 10-RES-JB
    11. 6958
    Prev
    Next
    INDEX
    Explanations

    verbs related to the act of spending or investing time, money, or effort

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spend" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.67
    LINE
    -0.65
    named
    -0.65
    Adds
    -0.62
    oké
    -0.58
    ensen
    -0.58
    Reviewer
    -0.57
    CO
    -0.56
    TEXTURE
    -0.55
    athy
    -0.54
    POSITIVE LOGITS
     eternity
    1.21
     winters
    1.04
     hours
    1.03
     summers
    1.03
     time
    0.97
     weekends
    0.96
     nights
    0.94
     untold
    0.94
    itures
    0.93
     YEAR
    0.91
    Activations Density 0.044%

    No Known Activations