INDEX

Explanations

reported speech and statements

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

-};

-0.68

horst

-0.60

KindOfClass

-0.58

einem

-0.58

utscher

-0.58

mdi

-0.57

PIA

-0.57

Pha

-0.56

 Morty

-0.55

 ſon

-0.55

POSITIVE LOGITS

sizeCache

0.63

the

0.61

“

0.56

 ProtoMessage

0.55

ecause

0.55

 censiti

0.54

щадь

0.54

esModule

0.53

 although

0.53

Activations Density 0.175%

reported speech and statements

No Comments

No Known Activations