INDEX

Explanations

references to insurance-related terms and concepts

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

"and" or a number

np_acts-logits-general · gemini-2.0-flash

abundance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

sizeCache

-0.82

ticularly

-0.74

 maupun

-0.70

 khususnya

-0.65

fjspx

-0.64

تقاوى

-0.64

Especially

-0.63

 Particularly

-0.62

XtraEditors

-0.61

 aught

-0.60

POSITIVE LOGITS

 lots

1.61

 plenty

1.59

lots

1.26

 LOTS

1.24

Lots

1.23

 ample

1.22

 tons

1.18

 Lots

1.17

plenty

1.17

Plenty

1.04

Activations Density 0.237%

references to insurance-related terms and concepts

"and" or a number

abundance

No Comments

No Known Activations