INDEX

Explanations

terms and concepts related to security

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

ukone

-0.72

 nahilalakip

-0.71

المناصب

-0.63

SpringBootTest

-0.62

солю

-0.58

 beginnetje

-0.58

mitives

-0.57

agissait

-0.57

وأضاف

-0.56

araman

-0.55

POSITIVE LOGITS

="{

0.65

FDA

0.60

UnsafeEnabled

0.60

 secure

0.59

RSpec

0.59

 tartalomajánló

0.58

 ModelExpression

0.57

HostException

0.57

]")]

0.56

arraycopy

0.56

Activations Density 0.101%

terms and concepts related to security

No Comments

No Known Activations