INDEX

Explanations

references to honor or recognition

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

 naselje

-0.65

äld

-0.64

 initComponents

-0.63

izop

-0.60

ußt

-0.60

etCode

-0.59

wiek

-0.59

 Leverkusen

-0.58

peka

-0.57

 Avril

-0.56

POSITIVE LOGITS

 honor

2.48

 HONOR

2.29

 honors

2.25

 Honor

2.24

 honour

2.21

honor

2.18

Honor

2.16

 honored

2.00

 Honour

1.94

hon

1.92

Activations Density 0.049%

references to honor or recognition

No Comments

No Known Activations