INDEX

Explanations

instances referring to leadership or notable roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 ſeveral

-0.62

 itſelf

-0.56

 Jefus

-0.54

 Combien

-0.54

SpringBootTest

-0.53

 various

-0.52

 Brecht

-0.52

 tqdm

-0.51

 interesting

-0.51

 Федерации

-0.50

POSITIVE LOGITS

 protoimpl

0.74

DockStyle

0.68

StoryboardSegue

0.67

SharedDtor

0.66

no

0.64

 ModelExpression

0.64

bindParam

0.63

 MainAxisSize

0.63

 nessun

0.63

 '\\;'

0.62

Activations Density 0.311%

instances referring to leadership or notable roles

No Comments

No Known Activations