INDEX

Explanations

phrases that emphasize 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

]")]

-0.68

advert

-0.63

)++;

-0.61

UnknownFieldSet

-0.61

quiel

-0.60

adalupe

-0.59

fjspx

-0.57

 juri

-0.57

 Waray

-0.57

 resourceCulture

-0.57

POSITIVE LOGITS

 should

1.22

should

1.10

 Should

1.05

Should

1.03

 shouldBe

0.92

 SHOULD

0.92

hould

0.91

 devriez

0.91

 shouldn

0.86

 deberían

0.84

Activations Density 0.305%

phrases that emphasize obligations or recommendations

No Comments

No Known Activations