INDEX

Explanations

concepts related to deception and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RefNanny

-0.66

 nakalista

-0.64

reportWebVitals

-0.64

万美元

-0.64

issance

-0.63

ActivityCompat

-0.63

kussion

-0.62

 defaultstate

-0.60

 небо

-0.58

 dinosaurio

-0.58

POSITIVE LOGITS

 deceptive

0.90

 trap

0.87

 misleading

0.86

 fooled

0.86

 mislead

0.85

 enga

0.84

 lure

0.84

 misled

0.82

 temptation

0.82

 illusion

0.81

Activations Density 0.295%

concepts related to deception and manipulation

No Comments

No Known Activations