INDEX

Explanations

repetitive instances of the word "because."

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

TagHelpers

-0.77

 Nestor

-0.72

stateProvider

-0.69

utnik

-0.69

moud

-0.67

 ſeveral

-0.66

olyte

-0.64

$_"

-0.64

 sundry

-0.64

 faſt

-0.64

POSITIVE LOGITS

 because

3.79

Because

3.56

 Because

3.49

because

3.49

 BECAUSE

3.23

 porque

3.20

 perché

2.69

 karena

2.63

porque

2.60

因为

2.58

Activations Density 0.072%

repetitive instances of the word "because."

No Comments

No Known Activations