INDEX

Explanations

words and phrases associated with matching and comparisons

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

"match" and its variations

np_acts-logits-general · gemini-2.0-flash

finding similarities or exact matches

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 newUser

-0.51

 незавершена

-0.50

execSQL

-0.44

PropertyChanging

-0.44

 />";

-0.43

omitempty

-0.43

Gog

-0.42

قایناق‌لار

-0.40

Werdegang

-0.40

getMenuInflater

-0.40

POSITIVE LOGITS

 match

2.47

match

2.36

 Match

2.30

Match

2.22

 MATCH

2.20

 matched

2.06

MATCH

2.06

 matching

2.05

 matches

2.02

 Matching

1.88

Activations Density 0.130%

words and phrases associated with matching and comparisons

"match" and its variations

finding similarities or exact matches

No Comments

No Known Activations