INDEX

Explanations

references to numbers and quantitative data

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

"For the" followed by a noun

np_acts-logits-general · gemini-2.0-flash

for the purpose/reason

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

encodeWith

-0.61

購入した

-0.55

ătă

-0.51

 TestBed

-0.50

めでとう

-0.48

queles

-0.48

setAccessible

-0.47

}})

-0.46

getcwd

-0.46

開催

-0.45

POSITIVE LOGITS

 purposes

1.84

 sake

1.81

purposes

1.48

 purpose

1.32

 Purposes

1.31

purpose

1.14

 reasons

1.10

Purpose

1.06

 Purpose

0.98

 Sake

0.98

Activations Density 0.203%

references to numbers and quantitative data

"For the" followed by a noun

for the purpose/reason

No Comments

No Known Activations

references to numbers and quantitative data

"For the" followed by a noun

for the purpose/reason

No Comments

No Known Activations