INDEX

Explanations

references to babies and related terms

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

esgue

-0.69

wikimedia

-0.64

hmig

-0.62

oshima

-0.61

}`

-0.61

yntaxException

-0.60

 InputDecoration

-0.60

 prior

-0.60

 nomina

-0.60

uttu

-0.59

POSITIVE LOGITS

 baby

2.30

 babies

2.21

 Baby

2.19

baby

2.18

Baby

2.15

 BABY

2.10

BABY

2.06

babies

1.82

 Babies

1.80

 bébé

1.74

Activations Density 0.037%

references to babies and related terms

No Comments

No Known Activations