INDEX

Explanations

repeated instances of the output command in programming-related text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

rungsseite

-0.78

Παραπομπές

-0.73

protoimpl

-0.67

Portail

-0.66

లాలు

-0.66

 bancaria

-0.66

Tide

-0.65

 envers

-0.65

########.

-0.64

 VizieR

-0.63

POSITIVE LOGITS

cout

1.13

大

0.79

 outlet

0.73

대

0.71

 cout

0.68

 Illinois

0.66

대

0.66

大

0.56

 nullptr

0.55

Illinois

0.54

Activations Density 0.181%

repeated instances of the output command in programming-related text

No Comments

No Known Activations