INDEX

Explanations

conjunctions, particularly the word "and" in various contexts

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

 createState

-0.72

athed

-0.66

WriteBarrier

-0.61

})));

-0.61

 facilité

-0.61

elerik

-0.60

 Backing

-0.60

 empe

-0.59

 ModelExpression

-0.59

Backing

-0.59

POSITIVE LOGITS

PreferredItem

0.69

 highly

0.59

HasAnnotation

0.56

newtheorem

0.54

蜒

0.52

 very

0.51

InjectAttribute

0.50

且

0.50

 Normdatei

0.49

 defaultstate

0.49

Activations Density 0.271%

conjunctions, particularly the word "and" in various contexts

No Comments

No Known Activations