INDEX

Explanations

phrases indicating understanding or realization

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

followed by "now"

np_acts-logits-general · gemini-2.0-flash

understanding now

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

::*;

-0.43

出版年

-0.40

jeti

-0.39

oltà

-0.38

sura

-0.37

czegó

-0.36

ってい

-0.36

anas

-0.35

 داشتم

-0.35

)}}{

-0.35

POSITIVE LOGITS

now

4.23

now

3.58

 теперь

3.26

Now

3.18

Now

3.18

 maintenant

3.06

 ahora

3.04

Теперь

3.01

 Теперь

2.97

 agora

2.86

Activations Density 1.526%

phrases indicating understanding or realization

followed by "now"

understanding now

No Comments

No Known Activations