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. 15689
    Prev
    Next
    INDEX
    Explanations

    keyword phrases related to financial and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial obligations and payments, particularly regarding child support and ransom situations

    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
     cannabin
    -0.67
     Lonely
    -0.66
    ãĤ¤ãĥĪ
    -0.63
     Ange
    -0.62
     Mate
    -0.62
     Hast
    -0.61
     Infect
    -0.61
    spect
    -0.60
     Spirits
    -0.60
    ITNESS
    -0.60
    POSITIVE LOGITS
    payer
    1.20
    payers
    1.18
     payable
    1.15
     payments
    1.15
     payment
    1.12
     repayment
    1.10
     payout
    1.09
     hike
    1.04
     refund
    1.02
     subsidy
    1.01
    Activations Density 0.300%

    No Known Activations