INDEX

Explanations

phrases related to privacy and data usage policies

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

Prepositions followed by conditions or requirements

np_acts-logits-general · gemini-2.0-flash

as required

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

WriteBarrier

-0.63

rungsseite

-0.57

ha

-0.54

DialogInterface

-0.53

…

-0.50

initState

-0.50

γέν

-0.49

StandardCharsets

-0.48

...

-0.48

tahui

-0.47

POSITIVE LOGITS

 itſelf

0.74

0.71

erapeu

0.69

 églises

0.67

 Houſe

0.66

 Site

0.64

 prêtres

0.63

 fubject

0.62

 neceffary

0.60

 iſt

0.60

Activations Density 0.230%

phrases related to privacy and data usage policies

Prepositions followed by conditions or requirements

as required

No Comments

No Known Activations