INDEX

Explanations

terms associated with illegal activities

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

 GenerationType

-1.08

 informée

-0.93

adə

-0.82

Efq

-0.79

VIAF

-0.78

RTLD

-0.78

#+#

-0.78

writerow

-0.74

ACGIH

-0.73

 kaarangay

-0.72

POSITIVE LOGITS

 illegal

0.67

 clearance

0.58

 vice

0.49

 area

0.48

 square

0.46

 Clearance

0.46

in

0.46

 officials

0.45

 fact

0.44

clearance

0.43

Activations Density 0.126%

terms associated with illegal activities

No Comments

No Known Activations