INDEX

Explanations

instances of the article "a" or "an" to identify the presence of descriptions or qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

alim

-0.47

roy

-0.47

ことです

-0.46

 pinulongan

-0.45

 Voulez

-0.45

ceğim

-0.45

lel

-0.43

 Short

-0.43

こと

-0.43

FloatField

-0.43

POSITIVE LOGITS

 Italijanski

0.85

MENAFN

0.80

 للاسماء

0.74

TintMode

0.71

ArrowToggle

0.71

Sebagai

0.71

 oprot

0.70



0.70

SOUNDBITE

0.69

 estekak

0.67

Activations Density 0.077%

instances of the article "a" or "an" to identify the presence of descriptions or qualifications

No Comments

No Known Activations