INDEX

Explanations

instances of errors and corrections in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

HtmlAttribute

-0.45

OuterClass

-0.45

 Initialized

-0.44

 relativ

-0.41

oc

-0.41

 approach

-0.39

burgo

-0.37

OrBuilder

-0.37

İY

-0.37

henswürdigkeiten

-0.36

POSITIVE LOGITS

 mistakenly

1.50

 incorrectly

1.33

 incorrect

1.32

 wrongly

1.30

 wrong

1.28

 mistake

1.25

 accidentally

1.25

 erroneously

1.25

 inadvertently

1.20

incorrect

1.19

Activations Density 0.494%

instances of errors and corrections in text

No Comments

No Known Activations