INDEX

Explanations

recurring references to 'day-to-day' activities and interactions

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

followed by "to"

np_acts-logits-general · gemini-2.0-flash

face-to-face connector phrases

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

 pinulongan

-0.77

новниш

-0.76

 оригіналу

-0.66

endphp

-0.65

SharedCtor

-0.64

 &___

-0.62

RenderAtEndOf

-0.62

 LUMP

-0.58

 oprot

-0.58

 مشين

-0.58

POSITIVE LOGITS

 flyknit

0.58

to

0.54

0.53

 προς

0.52

Tore

0.51

SizeMode

0.49

SqlSession

0.47

Rohy

0.45

toja

0.44

tora

0.43

Activations Density 0.190%

recurring references to 'day-to-day' activities and interactions

followed by "to"

face-to-face connector phrases

No Comments

No Known Activations