INDEX

Explanations

elements related to errors and discrepancies in documents

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

AndEndTag

-0.54

XtraBars

-0.52

GEBURTSDATUM

-0.51

 estimés

-0.50

はじめに

-0.49

rungsseite

-0.49

 stanovnika

-0.47

NameInMap

-0.46

lgari

-0.46

 StatefulWidget

-0.45

POSITIVE LOGITS

 errors

1.23

bug

1.21

 typos

1.20

 bugs

1.16

 flaw

1.15

 mistakes

1.13

bug

1.11

 flaws

1.11

 defects

1.10

 error

1.08

Activations Density 0.638%

elements related to errors and discrepancies in documents

No Comments

No Known Activations