INDEX

Explanations

words and phrases related to opposition or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

perature

-0.70

 BoxFit

-0.63

atimes

-0.62

SdkVersion

-0.61

 jScrollPane

-0.59

లాలు

-0.58

logrus

-0.57

Queryable

-0.56

 yourselves

-0.56

 pleinement

-0.55

POSITIVE LOGITS

 against

1.42

 opposes

1.40

 oppose

1.38

Against

1.37

 Against

1.35

against

1.27

 AGAINST

1.25

 melawan

1.19

 contre

1.16

 opposing

1.16

Activations Density 0.461%

words and phrases related to opposition or conflict

No Comments

No Known Activations