INDEX

Explanations

references to dresses and clothing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 AssemblyCulture

-0.88

 الحره

-0.81

">//

-0.61

TagMode

-0.61

nestjs

-0.61

esModule

-0.61

AutoScaleMode

-0.61

 <=",

-0.59

كويكب

-0.59

</tfoot>

-0.57

POSITIVE LOGITS

 clothing

2.46

 dress

2.42

 clothes

2.28

Dress

2.18

 dresses

2.15

 Dress

2.10

dress

2.09

 DRESS

2.08

 dressed

2.07

 Clothing

2.05

Activations Density 0.060%

references to dresses and clothing

No Comments

No Known Activations