INDEX

Explanations

phrases that express satisfaction or positive experiences

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

جغرافيا

-0.62

ValueStyle

-0.61

seamnă

-0.60

χρι

-0.57

 vocales

-0.55

ญี่ปุ่น

-0.54

 BoxDecoration

-0.53

couvrez

-0.53

Même

-0.53

":[{

-0.53

POSITIVE LOGITS

ukone

0.58

LookAnd

0.56

 betweenstory

0.53

Ẫ

0.50

engelsk

0.49

inguez

0.48

cshtml

0.47

zoic

0.46

 puddles

0.46

IANGLES

0.45

Activations Density 0.067%

phrases that express satisfaction or positive experiences

No Comments

No Known Activations