INDEX

Explanations

references to inner experiences or emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

HasKey

-0.76

 Harlow

-0.71

PPC

-0.71

 Mawr

-0.71

 Gantt

-0.67

ه‌اند

-0.65

posób

-0.64

PhysRevLett

-0.63

 tomu

-0.63

Geographie

-0.63

POSITIVE LOGITS

 Inside

2.30

 inside

2.25

Inside

2.24

inside

2.15

 INSIDE

2.15

INSIDE

1.96

 insides

1.42

 Dentro

1.33

 Outside

1.31

OUTSIDE

1.28

Activations Density 0.051%

references to inner experiences or emotions

No Comments

No Known Activations