INDEX

Explanations

words related to legal arguments and implications

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

ending in "-ing" after a verb

np_acts-logits-general · gemini-2.0-flash

verbs followed by ing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PickerController

-0.57

tifies

-0.55

criminate

-0.54

出版年

-0.53

ceği

-0.52

 за

-0.52

cherichia

-0.51

getBean

-0.51

ddots

-0.51

POSITIVE LOGITS

 CreateTagHelper

0.78

 متعلقه

0.76

 autorytatywna

0.69

存于互联网档案馆

0.67

 Theſe

0.64

 AssemblyCulture

0.62

 InputDecoration

0.62

principalColumn

0.61

 utafitiHapana

0.59

fromnode

0.58

Activations Density 0.287%

words related to legal arguments and implications

ending in "-ing" after a verb

verbs followed by ing

No Comments

No Known Activations