© 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. 19993
    Prev
    Next
    INDEX
    Explanations

    words related to earnings or income

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with earning or income, particularly in economic contexts

    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
     Shant
    -0.67
    alg
    -0.66
     interfering
    -0.65
    é¾įå¥ij士
    -0.65
     invasive
    -0.63
    debian
    -0.63
     Bengal
    -0.63
    MRI
    -0.63
    phal
    -0.62
    WT
    -0.62
    POSITIVE LOGITS
    hardt
    1.37
    Earn
    1.32
     Earn
    1.30
    ners
    0.96
    emouth
    0.89
    estead
    0.88
    estones
    0.87
    ership
    0.86
    sburg
    0.85
    baugh
    0.85
    Activations Density 0.005%

    No Known Activations