INDEX

Explanations

phrases indicating rarity or uniqueness among subjects or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

NewUrlParser

-0.71

Efq

-0.65

ſelf

-0.64

 leaſt

-0.64

 itſelf

-0.62

tvguidetime

-0.61

 étoit

-0.61

 myſelf

-0.59

middels

-0.59

onOptions

-0.59

POSITIVE LOGITS

 truly

0.65

 verdaderamente

0.60

 actually

0.58

 acceptable

0.55

truly

0.55

 wirklich

0.54

 really

0.54

 réellement

0.53

 genuinely

0.53

survi

0.52

Activations Density 0.327%

phrases indicating rarity or uniqueness among subjects or entities

No Comments

No Known Activations