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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 8158
    Prev
    Next
    INDEX
    Explanations

    instances of the word "offer" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of offers or proposals

    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
    cling
    -0.73
    ritical
    -0.67
     Unloaded
    -0.63
    heat
    -0.63
    capital
    -0.62
    avia
    -0.62
    ust
    -0.60
    luaj
    -0.60
    icent
    -0.59
     Headquarters
    -0.59
    POSITIVE LOGITS
     offers
    0.95
    pta
    0.82
     offer
    0.81
     condolences
    0.80
     offered
    0.80
    backs
    0.78
     offering
    0.78
     offerings
    0.76
    holder
    0.74
    rament
    0.73
    Activations Density 0.013%

    No Known Activations