INDEX

Explanations

references to water and its related attributes or processes

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

BeginContext

-0.92

zbęd

-0.91

BagConstraints

-0.89

 tartalomajánló

-0.89

 Vecchio

-0.87

 mẽ

-0.85

 myſelf

-0.85

iibo

-0.84

 Sabina

-0.84

)");

-0.81

POSITIVE LOGITS

 water

1.68

 Water

1.62

Water

1.59

water

1.52

 WATER

1.48

WATER

1.40

 waters

1.29

 Waters

1.28

 Waterman

1.25

Waters

1.23

Activations Density 0.066%

references to water and its related attributes or processes

No Comments

No Known Activations