INDEX

Explanations

instances of the word "is" and variations of "s" along with related affirmations or descriptors

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

 Soria

-0.53

 endIndex

-0.50

 Vallarta

-0.50

Partial

-0.49

 loginUser

-0.48

 <<<<<<<<<<<<<<

-0.48

geordnet

-0.48

rosine

-0.47

 tyrosine

-0.46

 Abolition

-0.46

POSITIVE LOGITS

AndEndTag

0.97

whats

0.97

 whats

0.93

 wireType

0.91

Whats

0.91

!("{

0.81

 Whats

0.78

UrlResolution

0.78

 Réponses

0.76

 '\\;'

0.76

Activations Density 0.109%

instances of the word "is" and variations of "s" along with related affirmations or descriptors

No Comments

No Known Activations