INDEX

Explanations

specific relationships and contextual dependencies between variables and categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

lichung

-0.60

writeField

-0.58

explique

-0.58

 unsalted

-0.55

 admires

-0.53

توض

-0.52

zubauen

-0.52

 layman

-0.51

väg

-0.51

 spéciale

-0.51

POSITIVE LOGITS

 actually

0.61

 ACTUALLY

0.58

 gynhyrchwyd

0.56

 available

0.56

 تضيفلها

0.55

parseFrom

0.52

 المعيارى

0.51

 resourceCulture

0.49

tra

0.48

cein

0.47

Activations Density 0.519%

specific relationships and contextual dependencies between variables and categories

No Comments

No Known Activations