INDEX

Explanations

variations of the word "photo."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 transfieras

-0.66

fotografía

-0.57

фотография

-0.52

 MainAxisSize

-0.51

rungsseite

-0.50

verages

-0.49

enumi

-0.49

hoten

-0.49

DataOutputStream

-0.49

randrange

-0.48

POSITIVE LOGITS

booth

0.70

 albums

0.67

realistic

0.65

 booth

0.65

 album

0.64

journalist

0.63

voltaic

0.61

montage

0.59

 volta

0.59

volta

0.59

Activations Density 0.144%

variations of the word "photo."

No Comments

No Known Activations

variations of the word "photo."

No Comments

No Known Activations