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. 8-RES-JB
    6. 21001
    Prev
    Next
    INDEX
    Explanations

    verbs related to purchasing or acquiring goods or services

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the act of buying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icone
    -0.79
    pmwiki
    -0.78
    uality
    -0.75
    icho
    -0.70
    uously
    -0.68
    ogen
    -0.66
     Slam
    -0.65
    etermin
    -0.64
    osa
    -0.64
    itous
    -0.63
    POSITIVE LOGITS
     groceries
    0.99
    iture
    0.98
     tickets
    0.91
     cheap
    0.78
     cheaply
    0.75
     price
    0.73
     goods
    0.72
     shares
    0.70
     certificates
    0.70
    backs
    0.69
    Activations Density 0.054%

    No Known Activations