INDEX

Explanations

timestamps or time-related information

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

Timestamps in transcripts

np_acts-logits-general · gemini-2.0-flash

transcripts and timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Geplaatst

-0.61

 surla

-0.55

UserScript

-0.54

iastes

-0.53

 kasarigan

-0.53

EndGlobalSection

-0.52

 resourceCulture

-0.51

ientras

-0.51

 الرياضيه

-0.51

AndroidJUnit

-0.50

POSITIVE LOGITS

Transcript

0.56

 Transcript

0.54

 transcript

0.51

transcript

0.43

 transcription

0.40

 transcripts

0.39

 transcribed

0.37

tvguidetime

0.36

 Orrell

0.35

LJ

0.34

Activations Density 0.700%

timestamps or time-related information

Timestamps in transcripts

transcripts and timestamps

No Comments

No Known Activations