INDEX

Explanations

instances of the word "which"

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

Followed by a verb or auxiliary verb

np_acts-logits-general · gemini-2.0-flash

which followed by a classifier

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



-0.72

-0.70

cnpj

-0.58

an

-0.57

 }^{[

-0.57

 mukana

-0.57

-0.55

 dàng

-0.55

-0.52

POSITIVE LOGITS

تقاوى

0.90

ίος

0.78

 means

0.76

istisches

0.75

úsqueda

0.73

ibatis

0.69

prüche

0.69

 BrowserModule

0.68

]**

0.67

adpleegd

0.67

Activations Density 0.168%

instances of the word "which"

Followed by a verb or auxiliary verb

which followed by a classifier

No Comments

No Known Activations