INDEX

Explanations

details related to clothing and appearance

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

before and/or after "and"

np_acts-logits-general · gemini-2.0-flash

clothing and accessories

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Dressed

-0.69

 dressed

-0.69

 vestito

-0.64

 clothed

-0.63

Dress

-0.63

+#+#

-0.62

服装

-0.61

 initComponents

-0.60

 DRESS

-0.59

 одежду

-0.59

POSITIVE LOGITS

 accessori

0.66

 shoes

0.64

 correctes

0.57

modb

0.53

Rujuakan

0.53

 accessor

0.53

 accessories

0.52

 footwear

0.52

 tartalomajánló

0.51

Становништво

0.51

Activations Density 0.083%

details related to clothing and appearance

before and/or after "and"

clothing and accessories

No Comments

No Known Activations