INDEX

Explanations

pronouns used in various contexts

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

 Cæsar

-0.56

ừ

-0.54

 Chrift

-0.53

Efq

-0.51

ettare

-0.50

 fince

-0.47

Yoh

-0.47

 Shakspeare

-0.47

 Jefus

-0.46

 Piers

-0.46

POSITIVE LOGITS

 تضيفلها

0.76

',$

0.72

 disambiguazione

0.71

verwijspagina

0.69

StructEnd

0.66

}{@

0.65

'],$

0.64

Билгалдахарш

0.63

 GetEnumerator

0.62

 Paglinawan

0.62

Activations Density 0.218%

pronouns used in various contexts

No Comments

No Known Activations