INDEX

Explanations

instances of uncertainty or confusion regarding a situation

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

"something"

np_acts-logits-general · gemini-2.0-flash

Something followed by elaboration

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

AutoScaleMode

-0.74

SuspendLayout

-0.52

ことは

-0.52

Jop

-0.51

IntoConstraints

-0.50

 defStyleAttr

-0.48

 Aufenthalt

-0.48

ことはない

-0.47

setVerticalGroup

-0.47

LookAnd

-0.46

POSITIVE LOGITS

 else

1.09

igshid

0.88

Else

0.78

IsContent

0.76

 akin

0.74

else

0.70

 very

0.69

ELSE

0.67

 ELSE

0.67

ETHING

0.65

Activations Density 0.069%

instances of uncertainty or confusion regarding a situation

"something"

Something followed by elaboration

No Comments

No Known Activations

instances of uncertainty or confusion regarding a situation

"something"

Something followed by elaboration

No Comments

No Known Activations