INDEX

Explanations

terms related to adaptability and adjusting to changing conditions

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

"adapt" and "adjust"

np_acts-logits-general · gemini-2.0-flash

adapt words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Rüyada

-0.53

zeera

-0.52

ItemGroup

-0.50

 Chwiliwch

-0.49

 Henn

-0.49

hoeddwyd

-0.48

herjee

-0.48

czegóły

-0.47

はじめに

-0.47

totalPages

-0.47

POSITIVE LOGITS

 adapts

0.98

 adjusts

0.98

Adap

0.94

 adapt

0.92

 adap

0.91

 Adap

0.90

Adjust

0.90

 adapting

0.90

 ADJUST

0.89

 Adapt

0.88

Activations Density 0.106%

terms related to adaptability and adjusting to changing conditions

"adapt" and "adjust"

adapt words

No Comments

No Known Activations