INDEX

Explanations

references to videos and media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

criture

-0.57

 InputDecoration

-0.56

 scrittura

-0.53

 escritura

-0.51

écriture

-0.49

SharedCtor

-0.49

 Readers

-0.49

 Reader

-0.47

gean

-0.47

 papir

-0.47

POSITIVE LOGITS

 video

1.51

 videos

1.47

 footage

1.40

video

1.34

Video

1.34

 Video

1.32

 Videos

1.21

videos

1.21

 vidéo

1.20

 VIDEO

1.19

Activations Density 0.440%

references to videos and media content

No Comments

No Known Activations