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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2-RES-JB
    6. 108
    Prev
    Next
    INDEX
    Explanations

    the term "lucrative."

    oai_token-act-pair · gpt-4-turbo

    words related to financial gain and profitability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial value and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptroller
    -0.66
    geist
    -0.64
    aration
    -0.64
    calling
    -0.64
    annis
    -0.63
    weak
    -0.62
    sil
    -0.62
    Listen
    -0.61
     Hyd
    -0.60
    prototype
    -0.59
    POSITIVE LOGITS
     lucrative
    1.07
     coveted
    0.99
     pric
    0.75
     plum
    0.73
    IOR
    0.71
     prizes
    0.71
     chunk
    0.71
     lure
    0.70
     juicy
    0.70
     payday
    0.68
    Activations Density 0.023%

    No Known Activations