INDEX

Explanations

phrases indicating fear, danger, and risk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

FunctionFlags

-0.58

 correctes

-0.57

sitivity

-0.57

 authService

-0.56

 motiv

-0.54

 فريبيس

-0.53

ValueStyle

-0.53

 OFDb

-0.52

]-->

-0.49

 autorytatywna

-0.49

POSITIVE LOGITS

 craindre

0.87

 feared

0.84

 incurring

0.76

 Gefahr

0.76

 rischi

0.75

 rischio

0.75

 lest

0.73

 threatens

0.72

Potential

0.70

 befür

0.70

Activations Density 0.231%

phrases indicating fear, danger, and risk

No Comments

No Known Activations