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. 1372
    Prev
    Next
    INDEX
    Explanations

    phrases related to selling or commerce

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sell."

    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
    aque
    -0.74
     Benedict
    -0.67
    arted
    -0.66
     Judicial
    -0.65
    ttp
    -0.65
    Jer
    -0.65
    reme
    -0.64
    jer
    -0.64
    involved
    -0.63
    asta
    -0.63
    POSITIVE LOGITS
     sell
    1.01
     sells
    0.96
     selling
    0.89
     sale
    0.86
     sales
    0.84
     price
    0.81
     prices
    0.78
    ãĥĥãĥī
    0.78
    Price
    0.77
     receipts
    0.77
    Activations Density 0.018%

    No Known Activations