INDEX

Explanations

different forms and contexts of the word "light."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 propOrder

-1.14

 оригіналу

-0.99

 bezeichneter

-0.96

 ProtoMessage

-0.96

ganu

-0.95

 שוליים

-0.94

 présidentielle

-0.91

 "..\..\..\

-0.90

__":

-0.90

 logique

-0.89

POSITIVE LOGITS

 Light

1.34

Light

1.27

 LIGHT

1.25

light

1.23

 light

1.13

LIGHT

1.13

 Lightfoot

1.06

 ligh

0.92

lights

0.91

 Licht

0.90

Activations Density 0.061%

different forms and contexts of the word "light."

No Comments

No Known Activations