INDEX

Explanations

references to Apple and its products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Calais

-0.76

Rüyada

-0.63

########.

-0.61

VIAF

-0.60

 eſt

-0.59

 GenerationType

-0.59

UnusedPrivate

-0.59

 Numa

-0.58

 Infórmanos

-0.57

 tevreden

-0.57

POSITIVE LOGITS

 Apple

3.48

Apple

3.21

 apple

2.96

apple

2.85

 APPLE

2.71

APPLE

2.43

 apples

2.26

 Apples

2.20

Apples

1.92

apples

1.88

Activations Density 0.092%

references to Apple and its products

No Comments

No Known Activations