INDEX

Explanations

scientific terminology related to research and experimental results

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

aarrggbb

-1.12

GEBURTSDATUM

-0.99

MigrationBuilder

-0.97

jspx

-0.92

SourceChecksum

-0.91

 '\\;'

-0.86

 يتيمه

-0.86

oredCriteria

-0.86

 nakalista

-0.86

+#+#

-0.84

POSITIVE LOGITS

for

2.16

สำหรับ

1.35

 für

1.35

 для

1.35

for

1.29

 untuk

1.28

 עבור

1.26

 bagi

1.16

 voor

1.14

dla

1.14

Activations Density 2.315%

scientific terminology related to research and experimental results

No Comments

No Known Activations