INDEX

Explanations

positive news or announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LastError

-0.51

HasBeenSet

-0.49

prä

-0.49

ثيق

-0.48

fering

-0.47

 springfox

-0.45

AccessorTable

-0.44

ContainsKey

-0.43

πάρχ

-0.43

ORA

-0.43

POSITIVE LOGITS

 news

2.95

news

2.18

 News

2.04

 NEWS

2.01

News

1.99

 noticia

1.84

 noticias

1.83

NEWS

1.79

 berita

1.72

 nieuws

1.71

Activations Density 0.160%

positive news or announcements

No Comments

No Known Activations