INDEX

Explanations

references to news sources and their articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

 borboleta

-0.38

 Soviet

-0.36

 Suomessa

-0.35

 skú

-0.35

Soorten

-0.35

 Table

-0.34

larımız

-0.34

 manuales

-0.33

 ejemplares

-0.33

 pilota

-0.33

POSITIVE LOGITS

 news

1.15

news

0.93

 News

0.86

 notícia

0.84

 NEWS

0.83

News

0.81

 headlines

0.81

NEWS

0.80

 noticias

0.80

 Newsroom

0.79

Activations Density 0.290%

references to news sources and their articles

No Comments

No Known Activations

references to news sources and their articles

No Comments

No Known Activations