INDEX

Explanations

keywords and terms related to health and safety, particularly those referencing products and possible reactions

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

"Smoke" and "Smoking"

np_acts-logits-general · gemini-2.0-flash

words starting with sm, especially smoke

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

userRepository

-0.80

al

-0.76

SuspendLayout

-0.75

lli

-0.71

 userRepository

-0.70

 Chaudh

-0.70

Hoi

-0.67

 Hase

-0.65

mber

-0.64

![](

-0.63

POSITIVE LOGITS

smoking

0.96

Smo

0.91

 smoking

0.89

 smokers

0.88

 smoke

0.88

 smoker

0.87

 Dickerson

0.84

enderror

0.82

 Permanente

0.81

smoke

0.81

Activations Density 0.557%

keywords and terms related to health and safety, particularly those referencing products and possible reactions

"Smoke" and "Smoking"

words starting with sm, especially smoke

No Comments

No Known Activations