INDEX

Explanations

references to specific individuals or entities, particularly those with the prefix "De."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

-0.94

Efq

-0.92

 leaſt

-0.82

 Chriſt

-0.80

 Houſe

-0.80

 faſt

-0.77

 Majefty

-0.77

 raiſ

-0.75

 ―――――

-0.74

 poffible

-0.74

POSITIVE LOGITS

De

2.90

De

2.65

 Де

1.21

DeV

1.12

DeL

1.01

Де

0.98

 DeWitt

0.91

Di

0.90

Del

0.89

 Dever

0.88

Activations Density 0.081%

references to specific individuals or entities, particularly those with the prefix "De."

No Comments

No Known Activations