INDEX

Explanations

contexts related to settings or environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

mbggenerated

-0.69

lifford

-0.66

xFC

-0.65

ListOf

-0.64

طيع

-0.63

בוד

-0.63

jores

-0.62

arao

-0.61

UNIDENTIFIED

-0.60

umbai

-0.60

POSITIVE LOGITS

 setting

2.87

 Setting

2.77

 SETTING

2.72

Setting

2.67

setting

2.62

SETTING

2.35

 settings

2.26

 Settings

2.00

 SETTINGS

1.85

settings

1.83

Activations Density 0.123%

contexts related to settings or environments

No Comments

No Known Activations