INDEX

Explanations

phrases that indicate complexity, challenges, and significant changes in a narrative or context

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

specific condition or characteristic

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

OGND

-0.77

 typelib

-0.71

 للمعارف

-0.71

 noDo

-0.70

#+#

-0.68

 Paglinawan

-0.68

 Italijanski

-0.68

GraphicsUnit

-0.68

 queſta

-0.68

 zwiſchen

-0.67

POSITIVE LOGITS

0.63

0.57

0.56

0.46

0.44

0.41

At

0.40

–

0.39

 gere

0.38

 because

0.38

Activations Density 0.138%

phrases that indicate complexity, challenges, and significant changes in a narrative or context

specific condition or characteristic

No Comments

No Known Activations

phrases that indicate complexity, challenges, and significant changes in a narrative or context

specific condition or characteristic

No Comments

No Known Activations