INDEX

Explanations

phrases related to safety and medical guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

ValueStyle

-0.59

SerializedName

-0.53

 tweaked

-0.53

 pretty

-0.52

anskje

-0.52

 Thankfully

-0.51

 Interestingly

-0.51

 just

-0.51

 arguably

-0.51

 hopefully

-0.50

POSITIVE LOGITS

 الرياضيه

0.72

ſelf

0.69

 متعلقه

0.67

 poichè

0.64

Never

0.63

Consult

0.61

 Moslem

0.61

ेशा

0.60

awsze

0.60

ATTENTION

0.60

Activations Density 0.170%

phrases related to safety and medical guidelines

No Comments

No Known Activations