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. 4-RES-JB
    6. 9821
    Prev
    Next
    INDEX
    Explanations

    payment-related terms and methods such as "via" online transactions

    oai_token-act-pair · gpt-3.5-turbo

    the term "via" indicating methods or means of connection or interaction

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

    No Comments

    Negative Logits
    stad
    -0.83
    thal
    -0.75
    naire
    -0.74
    TER
    -0.71
    Leary
    -0.69
    eared
    -0.69
    stal
    -0.66
    hound
    -0.66
     frogs
    -0.64
    ittal
    -0.63
    POSITIVE LOGITS
     Shutterstock
    0.84
     Via
    0.78
    creen
    0.75
     vide
    0.73
     Wikimedia
    0.73
     email
    0.72
     intermedi
    0.71
     Skype
    0.70
     multiple
    0.66
     modem
    0.66
    Activations Density 0.015%

    No Known Activations