INDEX

Explanations

references to specific characters or entities within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

webElement

-0.73

%;

-0.72

++

-0.70

XmlAccessType

-0.69

AnchorStyles

-0.67

enumi

-0.67

!")

-0.67

 unknownFields

-0.66

]))

-0.66

oa̍t

-0.65

POSITIVE LOGITS

 monté

0.53

 religieuses

0.53

 colorWith

0.52

 colorés

0.50

 třeba

0.50

 lalu

0.50

 reciente

0.49

 miliardi

0.49

 CreateTagHelper

0.48

 collè

0.48

Activations Density 1.303%

references to specific characters or entities within a narrative context

No Comments

No Known Activations