INDEX

Explanations

quotation marks and punctuation associated with dialogue

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

 Normdatei

-0.80

brigens

-0.79

aarrggbb

-0.75

 متعلقه

-0.68

IVEREF

-0.68

 myſelf

-0.66

 alfo

-0.65

AndEndTag

-0.65

 XNUMX

-0.64

 Adieu

-0.64

POSITIVE LOGITS

 sarcasm

0.49

 hearing

0.48

 acepción

0.45

Hearing

0.43

Laughter

0.42

Surprised

0.42

Confusion

0.42

Silence

0.42

闻言

0.41

 jakby

0.41

Activations Density 0.051%

quotation marks and punctuation associated with dialogue

No Comments

No Known Activations