INDEX

Explanations

descriptive phrases or attributes about places and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

WriteTagHelper

-0.67

PostConstruct

-0.56

WebElementEntity

-0.56

 hObject

-0.53

Спасылкі

-0.53

MigrationBuilder

-0.52

ⓘ

-0.52

FieldBuilder

-0.52

出版年

-0.50

 Brought

-0.49

POSITIVE LOGITS

 part

0.63

 said

0.61

 home

0.59

 notable

0.55

 estimated

0.54

 thought

0.52

 hjem

0.51

 responsible

0.51

 terbesar

0.50

 famous

0.49

Activations Density 0.456%

descriptive phrases or attributes about places and communities

No Comments

No Known Activations