INDEX

Explanations

elements related to injury and trauma

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

Japanese text referring to time

np_acts-logits-general · gemini-2.0-flash

apparently times

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

جغرافيا

-0.58

 ioutil

-0.52

 nascita

-0.51

mybatisplus

-0.51

 Apalagi

-0.50

ByPrimaryKey

-0.49

יוחד

-0.48

chige

-0.48

 hiszen

-0.47

ndorf

-0.47

POSITIVE LOGITS

 apparently

3.39

apparently

3.16

 Apparently

3.01

Apparently

2.89

 presumably

2.77

presumably

2.61

 evidently

2.56

 seems

2.51

 reportedly

2.46

 aparentemente

2.41

Activations Density 1.829%

elements related to injury and trauma

Japanese text referring to time

apparently times

No Comments

No Known Activations