INDEX

Explanations

references to Australia and associated entities or locations

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

 onCancelled

-0.58

+#+

-0.57

Démographie

-0.56

లాలు

-0.56

ⓘ

-0.55

 تانيه

-0.54

 zvuky

-0.53

్రామ

-0.51

 Distrikt

-0.50

voegd

-0.50

POSITIVE LOGITS

abestanden

0.71

matchCondition

0.69

InputTagHelper

0.64

 PopupWindow

0.62

 dollar

0.62

"""

0.62

</caption>

0.61

 Outback

0.59

HZ

0.58

 estimés

0.58

Activations Density 0.080%

references to Australia and associated entities or locations

No Comments

No Known Activations