INDEX

Explanations

references to the current year

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 للمعارف

-1.05

 itſelf

-1.01

Efq

-0.93

 purpoſe

-0.92

 Theſe

-0.88

 myſelf

-0.88

Eſ

-0.87

'{@

-0.84

 Reſ

-0.83

՚

-0.83

POSITIVE LOGITS

now

1.07

 today

1.03

 next

0.81

 tonight

0.79

today

0.75

hoy

0.75

Today

0.72

TODAY

0.72

今年

0.70

 ahora

0.69

Activations Density 0.235%

references to the current year

No Comments

No Known Activations