INDEX

Explanations

references to greatness or the concept of being 'great'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 صوتيه

-0.76

InputBorder

-0.60

 elsewhere

-0.59

 Aegean

-0.59

 Pharisees

-0.59

 Ferner

-0.58

RenderAtEndOf

-0.57

 Montmartre

-0.57

 Tangerang

-0.55

 sarees

-0.55

POSITIVE LOGITS

 great

4.42

great

4.08

Great

3.71

 Great

3.70

GREAT

3.43

 GREAT

3.40

 greats

2.03

 greate

1.96

 grande

1.96

 grandes

1.95

Activations Density 0.070%

references to greatness or the concept of being 'great'

No Comments

No Known Activations