INDEX

Explanations

contradictory or qualifying statements regarding various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 zwar

-0.71

UnusedPrivate

-0.68

bbene

-0.57

execSQL

-0.56

Unmarshaller

-0.56

تقاوى

-0.55

Sucesor

-0.55

PasswordEncoder

-0.54

 DbType

-0.53

 sice

-0.52

POSITIVE LOGITS

 also

0.81

 actively

0.70

 autorytatywna

0.70

also

0.70

Also

0.68

 vielmehr

0.67

 véritable

0.66

actively

0.66

 alſo

0.65

 også

0.65

Activations Density 0.307%

contradictory or qualifying statements regarding various topics

No Comments

No Known Activations