INDEX

Explanations

references to research papers and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

tagHelperRunner

-1.15

 autorytatywna

-1.10

ConstraintMaker

-1.09

OGND

-1.08

AndEndTag

-1.02

AddTagHelper

-0.98

Autoritní

-0.97

 дописавши

-0.97

complexContent

-0.97

 وتسجيلات

-0.96

POSITIVE LOGITS

we

0.62

you

0.45

 emphasis

0.43

 آمده

0.43

提到

0.43

中

0.40

ピール

0.39

اب

0.39

 اشار

0.39

 discover

0.39

Activations Density 0.323%

references to research papers and articles

No Comments

No Known Activations