INDEX

Explanations

references to specific figures, tables, and genetic data in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 typelib

-1.19

 Савезне

-1.15

 الرياضيه

-1.13

 unknownFields

-1.09

 ProtoMessage

-1.05

 дописавши

-1.01

 CreateTagHelper

-0.98

 Мексичка

-0.94

writeFieldEnd

-0.93

 ModelExpression

-0.93

POSITIVE LOGITS

0.65

\_

0.63

</u>

0.49

ayr

0.48

ia

0.48

ite

0.47

}{

0.47

Activations Density 0.340%

references to specific figures, tables, and genetic data in a scientific context

No Comments

No Known Activations