INDEX

Explanations

expressions related to giving or contributing

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

 للمعارف

-1.02

 ujednoznacz

-0.83

Cordialement

-0.77

 Bourgoin

-0.76

ţele

-0.76

Série

-0.74

Luong

-0.73

 Marcos

-0.73

luiting

-0.72

roidery

-0.70

POSITIVE LOGITS

Give

2.32

 Give

2.29

give

2.22

 give

2.19

 GIVE

2.07

 Giving

2.02

Giving

2.02

 gives

1.99

GIVE

1.98

giving

1.97

Activations Density 0.103%

expressions related to giving or contributing

No Comments

No Known Activations