INDEX

Explanations

references to citations or return statements in academic writing

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

"Return to text" or "Continue Reading"

np_acts-logits-general · gemini-2.0-flash

continue reading or return

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

السكان

-0.91

InitVars

-0.78

 ProtoMessage

-0.78

رشف

-0.77

qrstuvwxyz

-0.76

 oprot

-0.76

fromnode

-0.75

########.

-0.73

 groote

-0.72

lgari

-0.71

POSITIVE LOGITS

ÁND

0.47

 متعلقه

0.43

 ends

0.42

arit

0.42

0.41

zept

0.40

tric

0.38

quer

0.38

 zahl

0.38

Vidu

0.38

Activations Density 0.232%

references to citations or return statements in academic writing

"Return to text" or "Continue Reading"

continue reading or return

No Comments

No Known Activations