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. 3-RES-JB
    6. 2593
    Prev
    Next
    INDEX
    Explanations

    references to payment methods

    oai_token-act-pair · gpt-3.5-turbo

    references to methods of financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hma
    -0.77
    clude
    -0.77
    heimer
    -0.72
    Cola
    -0.70
     Monstrous
    -0.70
    otted
    -0.69
    ierre
    -0.68
     ns
    -0.67
     Mansion
    -0.65
    bum
    -0.65
    POSITIVE LOGITS
     payment
    1.13
     payments
    0.99
    payment
    0.96
     laundering
    0.92
     refunds
    0.87
     arrangements
    0.84
     debit
    0.82
     exch
    0.82
     transactions
    0.81
     receipt
    0.80
    Activations Density 0.027%

    No Known Activations