INDEX

Explanations

phrases related to uncertainty or questioning

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

End of sentences near conversational phrases

np_acts-logits-general · gemini-2.0-flash

questions starting with if

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

GEBURTSDATUM

-0.76

("

-0.63

yntaxException

-0.63

 LayoutInflater

-0.61

 باخ

-0.60

 doInBackground

-0.60

 („

-0.60

 transfieras

-0.59

ثة

-0.58

 (“

-0.56

POSITIVE LOGITS

Um

0.92

 Okay

0.90

So

0.85

Okay

0.84

 okay

0.84

Um

0.82

Uh

0.81

 Yeah

0.81

And

0.79

so

0.79

Activations Density 0.095%

phrases related to uncertainty or questioning

End of sentences near conversational phrases

questions starting with if

No Comments

No Known Activations