INDEX

Explanations

instances of past actions or states involving characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 الدولى

-0.69

AddHtmlAttribute

-0.69

 kaynağından

-0.62

 ostavi

-0.59

MarshalTo

-0.59

AndEndTag

-0.57



-0.57

Демографія

-0.57

 censiti

-0.55

ępnie

-0.54

POSITIVE LOGITS

 impending

1.40

 ready

1.32

即将

1.32

 imminent

1.26

 preparing

1.21

快要

1.19

 hendak

1.16

 Ready

1.15

Ready

1.11

准备

1.11

Activations Density 0.377%

instances of past actions or states involving characters

No Comments

No Known Activations