INDEX

Explanations

expressions related to formal statements or responses

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

Quotes followed by speech attribution

np_acts-logits-general · gemini-2.0-flash

reported speech

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

coro

-0.55

 jScrollPane

-0.55

 ведь

-0.48

意外と

-0.45

Tembelea

-0.45

 newbies

-0.44

[+]

-0.44

 sneaky

-0.44

ついで

-0.43

 UIKit

-0.43

POSITIVE LOGITS

 Roskov

0.69

tanleria

0.68

 itſelf

0.67

 pleaſure

0.65

nocześnie

0.65

DockStyle

0.63

 desaf

0.63

 regrettable

0.62

 pleinement

0.62

isContained

0.62

Activations Density 0.276%

expressions related to formal statements or responses

Quotes followed by speech attribution

reported speech

No Comments

No Known Activations