INDEX

Explanations

repeated patterns or specific sequences within text data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ECONDS

-0.58

 Olympia

-0.58

anor

-0.58

 journey

-0.56

 Paulus

-0.56

額

-0.56



-0.55

ური

-0.55

 Sinai

-0.55

Katalog

-0.55

POSITIVE LOGITS

]")]

0.85

https

0.72

ru

0.71

ter

0.71

 '\\;'

0.68

 https

0.67

0.66

ru

0.64

ⓘ

0.62

Ser

0.62

Activations Density 0.250%

repeated patterns or specific sequences within text data

No Comments

No Known Activations