INDEX

Explanations

instances of the word "and."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amsung

-0.68

 bint

-0.68

elfare

-0.67

okin

-0.67

eload

-0.66

endas

-0.65

ITECT

-0.64

 المعيارى

-0.64

<?

-0.63

팎

-0.63

POSITIVE LOGITS

 therefore

0.91

 although

0.86

 hence

0.75

 поэтому

0.71

 consequently

0.69

 thus

0.67

although

0.64

 this

0.62

 därför

0.62

therefore

0.61

Activations Density 0.567%

instances of the word "and."

No Comments

No Known Activations