INDEX

Explanations

mentions and contexts related to video content

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

video clips

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

apimachinery

-0.49

 ब्रेकडाउन

-0.45

 FetchType

-0.45

Soorten

-0.43

gouv

-0.43

ècie

-0.42

addPreferredGap

-0.42

BeginContext

-0.42

udging

-0.41

StylePriority

-0.40

POSITIVE LOGITS

 video

0.65

 Video

0.63

Video

0.59

 videos

0.58

 Videos

0.58

 VIDEO

0.56

VIDEO

0.54

videos

0.54

video

0.51

Videos

0.51

Activations Density 0.007%

mentions and contexts related to video content

video clips

No Comments

No Known Activations