INDEX

Explanations

phrases related to reports or sources in news articles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

tvguidetime

-0.80

TagHelper

-0.66

 glands

-0.63

"><?=

-0.62

FontOfSize

-0.62

دانشنامهٔ

-0.62

 AspNetCore

-0.61

didSet

-0.60

Földrajzportál

-0.60

PRWEB

-0.60

POSITIVE LOGITS

wsj

0.56

исленность

0.48

ieuses

0.47

Personendaten

0.46

AutoField

0.45

reuters

0.44

Autoritní

0.44

twimg

0.42

">//

0.41

eqn

0.41

Activations Density 0.138%

phrases related to reports or sources in news articles

No Comments

No Known Activations