© 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. 0-RES-JB
    11. 1077
    Prev
    Next
    INDEX
    Explanations

    keywords related to earning or making money

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to earning or income generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkage
    -0.66
     strang
    -0.66
     analogy
    -0.66
     Vaj
    -0.65
    yz
    -0.64
    DD
    -0.62
     Dup
    -0.62
     Arch
    -0.61
    aph
    -0.60
     containment
    -0.60
    POSITIVE LOGITS
     earn
    3.46
     earns
    2.35
     earning
    2.10
    Earn
    2.09
     earned
    2.07
     Earn
    1.77
    earned
    1.67
     earnings
    1.42
     accumulate
    1.37
     qualify
    1.36
    Activations Density 0.018%

    No Known Activations