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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 14389
    Prev
    Next
    INDEX
    Explanations

    references to situations involving payment or compensation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "paid" in various contexts related to employment or compensation

    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
    ierre
    -1.07
    oys
    -0.86
    erion
    -0.85
    ãĤ¼ãĤ¦ãĤ¹
    -0.82
    ä¸ī
    -0.71
    abulary
    -0.68
    orically
    -0.68
    qv
    -0.66
    onductor
    -0.66
    ombs
    -0.65
    POSITIVE LOGITS
     dividends
    0.93
    outs
    0.89
    checks
    0.89
     overtime
    0.88
     salaries
    0.86
     homage
    0.86
     royalties
    0.84
     tribute
    0.84
     dues
    0.83
     tuition
    0.83
    Activations Density 0.036%

    No Known Activations