INDEX

Explanations

phrases that connect or coordinate ideas, particularly involving "and" or "or"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 adipis

-0.60

 säl

-0.60

 igenom

-0.58

 nemlig

-0.58

EnableWeb

-0.58

 parseFrom

-0.58

 typelib

-0.57

 opinião

-0.57

 składa

-0.56

 vraie

-0.56

POSITIVE LOGITS

 الرياضيه

0.76

])))

0.59

')],

0.59

州市

0.58

 widespread

0.58

corresponding

0.58

 subsequent

0.58

 "..\..\

0.57

]})

0.57

 corresponding

0.56

Activations Density 0.769%

phrases that connect or coordinate ideas, particularly involving "and" or "or"

No Comments

No Known Activations