INDEX

Explanations

phrases indicating limitations in studies or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

-0.67

 تضيفلها

-0.57

BARA

-0.53

qrt

-0.53

َه

-0.51

 دیکھیے

-0.49

翡翠

-0.48

 kasarigan

-0.47

ִי

-0.47

tır

-0.47

POSITIVE LOGITS

 تانيه

1.03

 يتيمه

0.73

 ویکی‌پدیا

0.69

 كومونز

0.61

}]

0.60

contentLoaded

0.59

RegressionTest

0.58

'])->

0.58

istoitu

0.57

'],

0.57

Activations Density 0.595%

phrases indicating limitations in studies or arguments

No Comments

No Known Activations