INDEX

Explanations

elements related to comparisons or evaluations, particularly in the context of quantities or values

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

Text snippets followed by "Return to text"

np_acts-logits-general · gemini-2.0-flash

Return, Q, Answers, Less

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 يتيمه

-0.69

Билгалдахарш

-0.63

WebElementEntity

-0.62

новништво

-0.60

İstinadlar

-0.59

 Wartawan

-0.59

الحياه

-0.59

 résister

-0.57

Cyfarwyddwr

-0.57

プローチ

-0.57

POSITIVE LOGITS

 tartalomajánló

0.87

 سكانية

0.86

 متعلقه

0.72

parsedMessage

0.72

 CreateTagHelper

0.72

 bezeichneter

0.71

Hochspringen

0.68

RunAsync

0.68

MessageTagHelper

0.67

 समीक्षाओं

0.64

Activations Density 0.502%

elements related to comparisons or evaluations, particularly in the context of quantities or values

Text snippets followed by "Return to text"

Return, Q, Answers, Less

No Comments

No Known Activations