INDEX

Explanations

terms and phrases that suggest a relationship between actions and their consequences or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

verständlich

-0.70

expandindo

-0.68

Longest

-0.67

 المعيارى

-0.62

glLoadIdentity

-0.62

ască

-0.60

xffffff

-0.60

 uVar

-0.58

läufe

-0.58

Sparta

-0.57

POSITIVE LOGITS

 INDIC

1.06

 indicators

1.03

 signs

1.01

 SIGNS

0.97

indicator

0.95

 indicator

0.93

 Signs

0.92

 Indicators

0.92

indicators

0.91

 Indicates

0.89

Activations Density 0.175%

terms and phrases that suggest a relationship between actions and their consequences or implications

No Comments

No Known Activations