INDEX

Explanations

code-related terms, particularly those involving data structures and programming concepts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Negative Logits

 HasFactory

-0.57

FormTagHelper

-0.56

ktır

-0.56

 }}"></

-0.54

kmale

-0.54

oneofs

-0.52

resaid

-0.52

endforeach

-0.51

addEvent

-0.51

eki

-0.51

POSITIVE LOGITS

 because

1.26

 porque

1.06

because

1.03

Because

0.94

 Because

0.90

因为

0.87

 perché

0.87

porque

0.86

 perchè

0.85

 omdat

0.85

Activations Density 0.260%

code-related terms, particularly those involving data structures and programming concepts

No Known Activations