INDEX

Explanations

references to exposure to hazardous substances or conditions

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

"Exposure" or "exposed" followed by a preposition

np_acts-logits-general · gemini-2.0-flash

exposure to

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

 GenerationType

-0.66

niosek

-0.64

 चीज़ों

-0.60

IsDeleted

-0.59

TagMode

-0.57

verifyException

-0.56

MemoryWarning

-0.55

CellValue

-0.55

Eig

-0.53

isDeleted

-0.53

POSITIVE LOGITS

 exposure

1.42

exposure

1.36

Exposed

1.35

 Exposed

1.34

 Exposure

1.33

 exposing

1.30

 exposures

1.28

exposed

1.24

 exposed

1.22

Exposure

1.22

Activations Density 0.158%

references to exposure to hazardous substances or conditions

"Exposure" or "exposed" followed by a preposition

exposure to

No Comments

No Known Activations