INDEX

Explanations

references to time periods or durations

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

"[Time period] years later"

np_acts-logits-general · gemini-2.0-flash

time durations then later or ago

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 BrowserModule

-0.69

Personendaten

-0.53

saraba

-0.50

 XCTest

-0.50

 OkHttpClient

-0.50

 AppCompatTheme

-0.50

swire

-0.49

chou

-0.48

 NavController

-0.48

 dacia

-0.48

POSITIVE LOGITS

 later

1.39

ago

1.09

later

0.97

 senere

0.91

 LATER

0.88

 Later

0.87

 später

0.83

 senare

0.82

Later

0.81

 earlier

0.78

Activations Density 0.117%

references to time periods or durations

"[Time period] years later"

time durations then later or ago

No Comments

No Known Activations