INDEX

Explanations

phrases indicating obligations or recommendations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.78

]")]

-0.65

塘

-0.62

 disponibilités

-0.60

WebVitals

-0.59

kegaard

-0.59

IUrlHelper

-0.59

 resourceCulture

-0.57

SerializedSize

-0.57

FetchType

-0.56

POSITIVE LOGITS

 should

1.33

should

1.26

Should

1.15

 Should

1.12

 Deber

1.05

 shouldBe

0.99

 SHOULD

0.98

 deberían

0.98

 devriez

0.95

 Shouldn

0.94

Activations Density 0.286%

phrases indicating obligations or recommendations

No Comments

No Known Activations