INDEX

Explanations

references to underlying concepts or mechanisms in various contexts

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

underlying structures and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 useAppContext

-0.75

majánló

-0.68

évaluateur

-0.64

SBATCH

-0.63

contentLoaded

-0.60

 հղումներ

-0.59

 ainfi

-0.58

parsedMessage

-0.57

 Anſ

-0.57

arangay

-0.56

POSITIVE LOGITS

 underlying

2.19

underlying

1.98

 Underlying

1.93

Underlying

1.86

 underlie

1.27

 underlies

1.23

 underpin

0.95

 underneath

0.94

 beneath

0.85

Beneath

0.82

Activations Density 0.008%

references to underlying concepts or mechanisms in various contexts

underlying structures and concepts

No Comments

No Known Activations