INDEX

Explanations

terms associated with political or military actions, especially relating to covert operations or government involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ثيل

-0.49

CodedInputStream

-0.45

HMAC

-0.42

 VIAF

-0.42

fvar

-0.41

Imm

-0.39

RectangleBorder

-0.38

etate

-0.38

BagLayout

-0.38

Wally

-0.36

POSITIVE LOGITS

.*")]

0.83

NUMX

0.73

opsida

0.69

ftagPool

0.69

fromCharCode

0.68

 Majefty

0.67

>--}}

0.65

RegressionTest

0.64

 дописавши

0.64

+#+#

0.63

Activations Density 1.136%

terms associated with political or military actions, especially relating to covert operations or government involvement

No Comments

No Known Activations