INDEX

Explanations

terms related to smoking behavior and its implications for health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

躇

-0.88

userRepository

-0.77

ThemeOverlay

-0.75

 userRepository

-0.70

OCTOBER

-0.69

NullException

-0.69

NOVEMBER

-0.67

قایناق‌لار

-0.66

/*

-0.65

Celsius

-0.65

POSITIVE LOGITS

Smo

1.60

Smo

1.56

smo

1.34

smo

1.22

 smoker

1.20

 smoking

1.20

 smokers

1.13

smoking

1.11

SMITH

1.11

 smoke

1.10

Activations Density 0.209%

terms related to smoking behavior and its implications for health

No Comments

No Known Activations