INDEX

Explanations

phrases indicating reported speech or quotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

navbar

-0.49

-0.47

prozess

-0.44

pae

-0.43

рын

-0.43

cms

-0.42

…

-0.42

responseText

-0.41

AC

-0.41

TAA

-0.41

POSITIVE LOGITS

TagMode

1.21

 <=",

1.19

 متعلقه

1.02

########.

0.99

parsedMessage

0.94

:+:

0.94

 autorytatywna

0.93

 unknownFields

0.93

WebVitals

0.92

 通販

0.91

Activations Density 0.670%

phrases indicating reported speech or quotations

No Comments

No Known Activations