INDEX

Explanations

references to photographs or images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

brainly

-0.74

colgroup

-0.71

WebServlet

-0.67

WebVitals

-0.64

OGND

-0.58

qrstuvwxyz

-0.56

 CreateTagHelper

-0.54

 /\.(

-0.52

findpost

-0.52

 ویکی‌پدیای

-0.52

POSITIVE LOGITS

 depicting

1.27

 showing

1.19

 showcasing

1.00

showing

0.99

 illustrating

0.96

 depicts

0.95

 montrant

0.93

 portraying

0.92

 SHOWING

0.89

 Showing

0.88

Activations Density 0.433%

references to photographs or images

No Comments

No Known Activations