INDEX

Explanations

phrases indicating relationships and advantages in various contexts

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

Comes after the word "of"

np_acts-logits-general · gemini-2.0-flash

noun phrase "of" noun phrase

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

KommentareTeilen

-0.73

 iconFacebook

-0.69

 himſelf

-0.62

GEBURTS

-0.60

 myſelf

-0.60

 itſelf

-0.60

 Majefty

-0.58

Efq

-0.58

Alguna

-0.57

 hjälper

-0.57

POSITIVE LOGITS

 having

1.01

 using

0.92

Having

0.69

 Having

0.68

 this

0.68

Using

0.66

 doing

0.66

 AssemblyTitle

0.66

 utilizing

0.65

 taking

0.63

Activations Density 0.403%

phrases indicating relationships and advantages in various contexts

Comes after the word "of"

noun phrase "of" noun phrase

No Comments

No Known Activations