INDEX

Explanations

phrases indicating focal points or specific subjects within the text

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

"This" or "That" followed by a verb

np_acts-logits-general · gemini-2.0-flash

determiner followed by noun or verb

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 next

-0.54

 hemsida

-0.53

 poitrine

-0.50

next

-0.49

eneuve

-0.48

etsk

-0.48

KommentareTeilen

-0.48

orteur

-0.48

 acela

-0.48

dr

-0.48

POSITIVE LOGITS

 مشين

0.73

reportWebVitals

0.66

 تضيفلها

0.65

Personendaten

0.65

èdia

0.64

 kind

0.64

 متعلقه

0.63

 BrowserModule

0.62

omiast

0.61

 purpoſe

0.60

Activations Density 0.238%

phrases indicating focal points or specific subjects within the text

"This" or "That" followed by a verb

determiner followed by noun or verb

No Comments

No Known Activations