INDEX

Explanations

terms related to insurance coverage and policies

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

Prepositions linking causes and effects

np_acts-logits-general · gemini-2.0-flash

insurance coverage and loss

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

health

-0.50

 INSURANCE

-0.50

 health

-0.48

SUCCEEDED

-0.46

 matricula

-0.46

шь

-0.46

intura

-0.45

Insurance

-0.45

 insurance

-0.45

 Insurance

-0.44

POSITIVE LOGITS

 limits

0.70

 loss

0.66

 exposures

0.64

 coverage

0.61

 Limits

0.59

 Loss

0.58

Loss

0.57

Rifer

0.57

 bodily

0.57

hasMoreElements

0.56

Activations Density 0.258%

terms related to insurance coverage and policies

Prepositions linking causes and effects

insurance coverage and loss

No Comments

No Known Activations