INDEX

Explanations

references to multiple authors or studies in academic writing

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

 виправивши

-0.87

 lenker

-0.74

ReusableCell

-0.71

 &___

-0.69

 itſelf

-0.68

bootstrapcdn

-0.67

хьтан

-0.67

 myſelf

-0.67

OGND

-0.66

دانشنامهٔ

-0.62

POSITIVE LOGITS

 publiés

0.56

sumowanie

0.56

 pylori

0.56

 годов

0.52

همچنین

0.52

 scalars

0.52

 econômica

0.52

 interesar

0.52

hringer

0.52

enido

0.51

Activations Density 0.116%

references to multiple authors or studies in academic writing

No Comments

No Known Activations