INDEX

Explanations

phrases indicating similarity or comparison

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

"similarly", "likewise", or "the same" followed by a verb

np_acts-logits-general · gemini-2.0-flash

likewise and similarly statements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

了一個

-0.34

ger

-0.34

 colheres

-0.33

 duquel

-0.33

 ſhall

-0.32

PACKET

-0.31

 disturbance

-0.31

 bruk

-0.30

Etter

-0.30

 quedaron

-0.30

POSITIVE LOGITS

Likewise

0.86

 Likewise

0.79

Similarly

0.79

 likewise

0.75

 similarly

0.74

 Similarly

0.73

 CreateTagHelper

0.73

 AssemblyCulture

0.68

 Ebenso

0.67

 propOrder

0.64

Activations Density 0.498%

phrases indicating similarity or comparison

"similarly", "likewise", or "the same" followed by a verb

likewise and similarly statements

No Comments

No Known Activations