INDEX

Explanations

references to statements made by officials or sources in reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

TagMode

-0.66

+#+#

-0.57

 joaat

-0.43

 بيها

-0.41

 retra

-0.39

лександ

-0.38

maten

-0.38

LEncoder

-0.37

 يتيمه

-0.37

ReusableCell

-0.37

POSITIVE LOGITS

reportWebVitals

0.72

Попис

0.71

 gynhyrchwyd

0.70

 kasarigan

0.68

Demografía

0.68

 "..\..\..\

0.67

 saurait

0.66

دانشنامهٔ

0.65

 Italijanski

0.65

Enllaces

0.63

Activations Density 0.089%

references to statements made by officials or sources in reports

No Comments

No Known Activations