INDEX

Explanations

sections of structured data or tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

insic

-0.73

 utafitiHapana

-0.71

 objectForKey

-0.64

améli

-0.59

érêt

-0.58

accro

-0.56

 >=",

-0.55

ंदीखरीदारी

-0.55

namentales

-0.55

 réduite

-0.54

POSITIVE LOGITS

SequentialGroup

0.70

IsMutable

0.63

URLException

0.60

økt

0.58

queryInterface

0.55

consulté

0.55

 ProtoMessage

0.51

 TextInputType

0.50

 ModelExpression

0.50

Activations Density 0.110%

sections of structured data or tables

No Comments

No Known Activations