INDEX

Explanations

terms related to power measurements and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tvguidetime

-0.72

rungsseite

-0.71

 &___

-0.64

ございません

-0.61

 елның

-0.57

 замо

-0.55

SwingConstants

-0.55

DropColumn

-0.55

 autorytatywna

-0.55

 Sykes

-0.53

POSITIVE LOGITS

 wattage

1.05

 watts

0.97

 watt

0.96

Watt

0.86

watts

0.82

 Watt

0.81

Power

0.79

watt

0.78

 Power

0.76

Watts

0.73

Activations Density 0.264%

terms related to power measurements and specifications

No Comments

No Known Activations