INDEX

Explanations

terms related to credit ratings and financial services for individuals

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"Credit" or "poor" appearing in text

np_acts-logits-general · gemini-2.0-flash

credit score issues

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ыгана

-0.62

XmlAccessType

-0.61

 ligiloj

-0.51

الحياه

-0.48

 EconPapers

-0.47

NameInMap

-0.47

 UIKit

-0.47

OptionsMenu

-0.47

 Leich

-0.47

éraires

-0.45

POSITIVE LOGITS

 poor

0.91

 Poor

0.87

 credit

0.86

Poor

0.86

 POOR

0.85

credit

0.85

 CREDIT

0.82

 Improving

0.79

Credit

0.77

 Credit

0.77

Activations Density 0.118%

terms related to credit ratings and financial services for individuals

"Credit" or "poor" appearing in text

credit score issues

No Comments

No Known Activations