INDEX

Explanations

references to historical political events and figures, particularly involving covert operations and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 tiết

-0.44

â

-0.44

esgue

-0.43

__":

-0.42

 componenti

-0.42

 Boys

-0.41

sillon

-0.41

ï

-0.40

かというと

-0.40

 service

-0.40

POSITIVE LOGITS

IUrlHelper

1.00

webElementXpaths

0.95

 AssemblyCulture

0.88

 ویکی‌پدی

0.81

تقاوى

0.81

 للاسماء

0.76

WithIOException

0.75

########.

0.74

Jeografia

0.73

Geplaatst

0.71

Activations Density 1.417%

references to historical political events and figures, particularly involving covert operations and conflicts

No Comments

No Known Activations