INDEX

Explanations

mentions of Twitter and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

✨:

-0.81

 rêves

-0.75

 Meld

-0.74

 postId

-0.74

χε

-0.74

 Brenn

-0.73

 fehl

-0.73

\":\"

-0.72

 mourir

-0.71

Vidite

-0.71

POSITIVE LOGITS

 Twitter

2.19

Twitter

2.05

twitter

1.81

 twitter

1.77

TWITTER

1.56

 TWITTER

1.49

witter

1.01

ツイッター

0.74

推特

0.72

ิลปะ

0.68

Activations Density 0.055%

mentions of Twitter and related terms

No Comments

No Known Activations