INDEX

Explanations

references to upper or lower regions and their associated characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

jooq

-0.68

tanleria

-0.67

 zirc

-0.67

PreferredItem

-0.67

المكان

-0.63

IndentedString

-0.63

 Wikimedijinoj

-0.62

Smarty

-0.61

ýl

-0.61

 Réponses

-0.60

POSITIVE LOGITS

 bound

0.76

bound

0.68

Bound

0.67

 Upper

0.65

MOST

0.63

 limit

0.61

most

0.61

case

0.58

 upper

0.57

cased

0.57

Activations Density 0.094%

references to upper or lower regions and their associated characteristics

No Comments

No Known Activations