INDEX

Explanations

the repeated mention of the word "ago" indicating references to time in the past

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

complexContent

-0.60

astéroïdes

-0.56

matchCondition

-0.55

Diweddarwch

-0.55

 незавершена

-0.51

AddTagHelper

-0.50

estacks

-0.47

 Compl

-0.46

دانشنامهٔ

-0.46

AnimationsModule

-0.46

POSITIVE LOGITS

ago

2.88

 geleden

1.41

ago

1.41

Ago

1.38

Ago

1.33

AGO

1.28

 назад

1.13

AGO

1.02

年前

0.90

 earlier

0.88

Activations Density 0.033%

the repeated mention of the word "ago" indicating references to time in the past

No Comments

No Known Activations