© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7018
    Prev
    Next
    INDEX
    Explanations

    financial terms and details related to covering costs or expenses

    oai_token-act-pair · gpt-3.5-turbo

    financial costs and expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.97
    ãĤ¼ãĤ¦ãĤ¹
    -0.90
    Õ
    -0.83
    sov
    -0.82
    raq
    -0.82
    strong
    -0.82
    weak
    -0.81
    ESE
    -0.80
    odox
    -0.79
    rust
    -0.78
    POSITIVE LOGITS
     expenses
    1.55
     fees
    1.35
     postage
    1.35
     lodging
    1.30
     depreciation
    1.26
     taxes
    1.26
     upkeep
    1.23
     salaries
    1.23
     costs
    1.20
     travel
    1.19
    Activations Density 0.245%

    No Known Activations