INDEX

Explanations

references to "other" or alternative options, entities, or aspects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 itself

-0.75

 each

-0.71

 others

-0.71

others

-0.70

itself

-0.70

 оригіналу

-0.68

Others

-0.67

 Others

-0.66

other

-0.66

 both

-0.65

POSITIVE LOGITS

worldly

1.63

 than

1.28

 similar

1.03

 niż

0.99

Than

0.98

 THAN

0.94

than

0.93

 similarly

0.91

 kuin

0.89

similar

0.87

Activations Density 0.230%

references to "other" or alternative options, entities, or aspects

No Comments

No Known Activations