INDEX

Explanations

specific film titles or names of notable works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-1.13

IndentedString

-1.07

ThroughAttribute

-0.98

LookAnd

-0.96

StructEnd

-0.95

fjspx

-0.87

BeginContext

-0.87

PreferredItem

-0.85

oredCriteria

-0.84

الإنجليزية

-0.83

POSITIVE LOGITS

 adalah

0.57

 merupakan

0.53

Pods

0.48

 представляет

0.47

 llaman

0.47

是一個

0.45

 rapides

0.45

 convertirse

0.44

an

0.44

 emerge

0.43

Activations Density 0.412%

specific film titles or names of notable works

No Comments

No Known Activations