INDEX

Explanations

references to ratings, particularly star ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 itſelf

-0.96

 Paglinawan

-0.89

 Majefty

-0.88

 purpoſe

-0.87

 poffible

-0.85

 myſelf

-0.81

 doubtnut

-0.80

 Monfieur

-0.80

 auffi

-0.80

 uſed

-0.79

POSITIVE LOGITS

intios

0.56

gameserver

0.54

0.51

0.50

 nổ

0.49

0.48

 समीक्षाओं

0.48

JspWriter

0.48

 Five

0.46

Activations Density 0.477%

references to ratings, particularly star ratings

No Comments

No Known Activations