INDEX

Explanations

phrases and variations of the word "what."

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

Aze

-0.71

 Verge

-0.68

 reminder

-0.68

 Brea

-0.67

 Moors

-0.67

erl

-0.64

es

-0.63

EES

-0.62

 Jolie

-0.62

 Crocodile

-0.61

POSITIVE LOGITS

 what

2.27

what

2.11

 WHAT

2.05

WHAT

1.98

What

1.90

 What

1.86

whats

1.30

 whats

1.17

Whats

1.09

 hvad

1.09

Activations Density 0.100%

phrases and variations of the word "what."

No Comments

No Known Activations