INDEX

Explanations

phrases related to loss and searching for individuals

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

Japanese text followed by "を"

np_acts-logits-general · gemini-2.0-flash

objects followed by verbs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

theless

-0.59

UserScript

-0.58

 >=",

-0.56

AccessorTable

-0.55

StoryboardSegue

-0.55

hical

-0.55

 iload

-0.54

bleib

-0.54

 kasarigan

-0.53

Dibrom

-0.53

POSITIVE LOGITS

devamını

0.91

we

0.65

ől

0.62

можно

0.57

meyi

0.57

 можно

0.56

曖昧さ回避

0.55

 слід

0.55

 следует

0.54

 trzeba

0.54

Activations Density 0.027%

phrases related to loss and searching for individuals

Japanese text followed by "を"

objects followed by verbs

No Comments

No Known Activations