INDEX

Explanations

references to episodes in a series or show

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

episode

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 financeira

-0.63

 algemene

-0.55

 braços

-0.52

 FirebaseAuth

-0.51

🏼

-0.50

 braço

-0.49

databind

-0.49

 ağaç

-0.48

 pintor

-0.47

 matemáticas

-0.47

POSITIVE LOGITS

 episode

1.30

 episodes

1.27

 Episode

1.13

 Episodes

1.09

Episode

1.09

episode

1.07

Episodes

1.03

episodes

0.97

 EPISODE

0.95

pisode

0.93

Activations Density 0.007%

references to episodes in a series or show

episode

No Comments

No Known Activations