INDEX

Explanations

references to locations and geographic features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

Efq

-0.87

 myſelf

-0.86

 المعيارى

-0.83

 poffible

-0.79

 Reſ

-0.77

 itſelf

-0.77

queryInterface

-0.77

Spoljašnje

-0.77

Eſ

-0.75

 photolibrary

-0.75

POSITIVE LOGITS

<eos>

0.89

eder

0.49

...

0.46

KeyEvent

0.45

Box

0.45

ke

0.44

cloudflare

0.44

Mo

0.43

...

0.43

Activations Density 0.037%

references to locations and geographic features

No Comments

No Known Activations