INDEX

Explanations

sequences of characters or codes that are likely associated with programming or technical terms

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

 ModelExpression

-0.94

 kasarigan

-0.77

 ddelweddau

-0.73

 تضيفلها

-0.63

 spé

-0.59

 pourtant

-0.59

contentLoaded

-0.58

NameInMap

-0.58

Rhestr

-0.58

iblichen

-0.56

POSITIVE LOGITS

ActionCreators

0.52

 Link

0.52

璨

0.49

 링크

0.49

TabIndex

0.47

étaro

0.47

фраструк

0.47

 שוליים

0.46

Einzelnachweise

0.46

 link

0.46

Activations Density 0.197%

sequences of characters or codes that are likely associated with programming or technical terms

No Comments

No Known Activations