INDEX

Explanations

positive descriptions and high ratings related to fashion and aesthetics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-1.25

 tartalomajánló

-1.20

 المعيارى

-1.16

 فريبيس

-1.10

تقاوى

-1.09

 Audiodateien

-1.08

RenderAtEndOf

-1.06

 ProtoMessage

-1.06

RectangleBorder

-1.04

OGND

-1.04

POSITIVE LOGITS

and

0.47

0.45

0.44

lo

0.39

up

0.39

fo

0.37

lo

0.36

he

0.36

of

0.36

Activations Density 1.148%

positive descriptions and high ratings related to fashion and aesthetics

No Comments

No Known Activations