INDEX

Explanations

the prefix 'un-' indicating negation or the absence of a quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 ainfi

-1.19

 Theſe

-1.13

 myſelf

-1.08

 becauſe

-1.06

 MainAxisSize

-1.05

 ſche

-1.02

 itſelf

-1.01

 ་་

-1.01

styleType

-1.00

 auffi

-0.96

POSITIVE LOGITS

Un

1.88

un

1.85

Un

1.65

UN

1.63

un

1.53

UN

1.36

Uni

0.97

有不

0.95

Pre

0.92

0.89

Activations Density 0.054%

the prefix 'un-' indicating negation or the absence of a quality

No Comments

No Known Activations