INDEX

Explanations

phrases introducing examples or instances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ymce

-0.69

 reaſon

-0.60

 sauvages

-0.59

 uska

-0.59

 houſe

-0.59

'<?

-0.58

↻

-0.58

 poffible

-0.57

 cauſe

-0.57

andidates

-0.56

POSITIVE LOGITS

tamment

0.74

 notably

0.73

 Particularly

0.71

besondere

0.71

 particularly

0.69

particularly

0.68

 insbesondere

0.68

 especially

0.68

 principalmente

0.68

especially

0.65

Activations Density 0.392%

phrases introducing examples or instances

No Comments

No Known Activations