INDEX

Explanations

questions and inquiries related to knowledge and awareness

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

Asks a question or implies a question

np_acts-logits-general · gemini-2.0-flash

questions asking for information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

bootstrapcdn

-0.51

 verrez

-0.50

 mijne

-0.47

 voorbere

-0.46

 particulières

-0.43

medriver

-0.42

PostExecute

-0.42

 outono

-0.41

tonode

-0.40

="@+

-0.40

POSITIVE LOGITS

1.11

?”

0.87

?"

0.86

？

0.80

?\\

0.80

؟

0.79

?)

0.79

?(

0.78

%?

0.78

?</

0.78

Activations Density 0.253%

questions and inquiries related to knowledge and awareness

Asks a question or implies a question

questions asking for information

No Comments

No Known Activations