INDEX

Explanations

questions and expressions of uncertainty about decision-making or problem-solving

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

Asking how to do something

np_acts-logits-general · gemini-2.0-flash

how to do

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

UrlResolution

-0.59

 ExecuteAsync

-0.50

UpInside

-0.49

CPtr

-0.48

 consultato

-0.48

DataAnnotations

-0.47

 Biôgrafia

-0.47

EndContext

-0.47

ądź

-0.46

 مرئيه

-0.46

POSITIVE LOGITS

 should

1.03

 Should

1.00

should

0.99

Should

0.94

TagMode

0.80

 Shall

0.77

 shall

0.76

 SHOULD

0.74

shall

0.74

to

0.72

Activations Density 0.217%

questions and expressions of uncertainty about decision-making or problem-solving

Asking how to do something

how to do

No Comments

No Known Activations