INDEX

Explanations

the prefix "un" in words, indicating negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Portale

-0.78

 myſelf

-0.75

 JAXBElement

-0.74

 itſelf

-0.73

 desgracia

-0.72

ISupport

-0.70

glTexCoord

-0.69

Portail

-0.68

 OCLC

-0.67

 zelve

-0.67

POSITIVE LOGITS

un

1.08

una

0.88

 North

0.64

Una

0.62

Una

0.56

startActivity

0.50

未

0.48

থ্য

0.48

::$

0.48

AMED

0.46

Activations Density 0.097%

the prefix "un" in words, indicating negation

No Comments

No Known Activations