INDEX

Explanations

phrases related to avoiding negative situations or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 publiques

-0.70

 extérieures

-0.67

 privées

-0.66

Mur

-0.66

mesg

-0.65

 Sutherland

-0.65

 vertes

-0.64

chromedriver

-0.63

 credentials

-0.63

licenses

-0.62

POSITIVE LOGITS

avoid

1.61

 Avoid

1.59

Avoid

1.55

 avoid

1.54

 AVOID

1.52

 avoiding

1.49

 avoidance

1.43

 Avoidance

1.41

 avoided

1.40

 avoids

1.37

Activations Density 0.099%

phrases related to avoiding negative situations or outcomes

No Comments

No Known Activations