INDEX

Explanations

phrases that indicate repetition or frequency of occurrence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

findElement

-0.81

 Beans

-0.71

ープ

-0.71

Fixtures

-0.71

Wpf

-0.70

 Tint

-0.69

énario

-0.66

тература

-0.66

🐥

-0.66

jms

-0.66

POSITIVE LOGITS

 Over

1.76

 over

1.74

 OVER

1.74

Over

1.68

over

1.64

OVER

1.48

 Overs

1.46

overs

1.33

 Overton

1.27

Overs

1.25

Activations Density 0.107%

phrases that indicate repetition or frequency of occurrence

No Comments

No Known Activations