INDEX

Explanations

various forms of the word "burn" in different contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-0.75

XmlEnum

-0.70

 חיצוניים

-0.70

 ujednoznacz

-0.69

+#+#

-0.68

 disambiguazione

-0.68

ValueStyle

-0.68

stateProvider

-0.67

dini

-0.65

 تانيه

-0.64

POSITIVE LOGITS

ished

0.72

 bridges

0.69

 Burns

0.66

 burns

0.66

 burn

0.64

 bridge

0.63

 BURN

0.61

 Burn

0.60

 burned

0.59

 burnt

0.58

Activations Density 0.080%

various forms of the word "burn" in different contexts

No Comments

No Known Activations