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. 18251
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial refunds and refund processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to refunds and refund processes

    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
    Downloadha
    -0.71
    jun
    -0.65
    intel
    -0.64
    anto
    -0.62
     assassinated
    -0.62
    unin
    -0.62
     knot
    -0.61
    chin
    -0.60
     convol
    -0.60
    AST
    -0.60
    POSITIVE LOGITS
     refunds
    1.04
    able
    1.03
     refund
    0.99
     Guarant
    0.85
    ees
    0.81
     invoice
    0.78
     postage
    0.78
     receipt
    0.77
    ivable
    0.76
     royalties
    0.75
    Activations Density 0.031%

    No Known Activations