INDEX

Explanations

the word "pro" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

+#+#

-0.93

astify

-0.70

LLocation

-0.69

UrlEncoded

-0.68

rrggbb

-0.68

zelf

-0.67

 CreateTagHelper

-0.67

 onCancelled

-0.66

存于互联网档案馆

-0.66

لينكات

-0.66

POSITIVE LOGITS

pro

0.78

pro

0.73

Pro

0.68

Pro

0.61

PRO

0.59

PRO

0.53

ʊ

0.45

 rata

0.44

prometheus

0.44

 grammi

0.43

Activations Density 0.094%

the word "pro" in various contexts

No Comments

No Known Activations

the word "pro" in various contexts

No Comments

No Known Activations