INDEX

Explanations

references to comparative or relational phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Neo

-0.59

'',

-0.57

loat

-0.57

Gim

-0.56

 useStyles

-0.56

colar

-0.56

 Acorn

-0.55

KN

-0.54

 Epis

-0.54

++

-0.53

POSITIVE LOGITS

 respectively

3.66

respectively

3.32

 respectivamente

2.98

 respectivement

2.61

 respective

2.10

 соответственно

1.87

 rispet

1.86

 respec

1.73

respective

1.70

分别

1.56

Activations Density 0.069%

references to comparative or relational phrases

No Comments

No Known Activations