INDEX

Explanations

phrases indicating varying levels of approval or disapproval

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

bav

-0.43

ềm

-0.41

lname

-0.41

Key

-0.40

 petits

-0.39

Key

-0.38

IONES

-0.38

HasAnnotation

-0.38

sig

-0.38

isOk

-0.38

POSITIVE LOGITS

//

0.83

Lähteet

0.79

 Roskov

0.71

 שוליים

0.71

 intptr

0.70

obviously

0.70

 obviously

0.70

הערות

0.70

 Wikimedijinoj

0.67

argout

0.67

Activations Density 0.461%

phrases indicating varying levels of approval or disapproval

No Comments

No Known Activations