INDEX

Explanations

phrases indicating positive assessments or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Obrázky

-0.71

OCS

-0.57

igus

-0.55

UnusedPrivate

-0.54

pago

-0.54

enegro

-0.53

 Eder

-0.52

Efq

-0.52

 againſt

-0.52

Expecting

-0.51

POSITIVE LOGITS

 good

0.74

دانشنامهٔ

0.69

 BorderRadius

0.68

enschappen

0.67

"}")

0.66

 الرياضيه

0.65

 buen

0.65

تقاوى

0.65

 nice

0.64

')):

0.64

Activations Density 0.080%

phrases indicating positive assessments or recommendations

No Comments

No Known Activations