INDEX

Explanations

phrases indicating something concealed or hidden, particularly those starting with "behind."

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

"behind"

np_acts-logits-general · gemini-2.0-flash

behind

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

sdag

-0.60

 viewDidLoad

-0.59

 hâte

-0.58

Tikang

-0.56

 Chwiliwch

-0.55

 ấm

-0.54

 SafeMath

-0.53

 pelajaran

-0.53

 Hummel

-0.52

%)$

-0.51

POSITIVE LOGITS

 Behind

0.97

 behind

0.97

 BEHIND

0.96

Behind

0.89

behind

0.81

 derrière

0.65

 front

0.62

 fronte

0.55

 covers

0.54

 dietro

0.53

Activations Density 0.102%

phrases indicating something concealed or hidden, particularly those starting with "behind."

"behind"

behind

No Comments

No Known Activations