INDEX

Explanations

references to news organizations and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

autaire

-0.55

mopol

-0.54

metido

-0.53

 Belajar

-0.53

NSYLVANIA

-0.52

TIMORE

-0.51

 familiarize

-0.49

irable

-0.49

 Zusammen

-0.49

voll

-0.49

POSITIVE LOGITS

 newspaper

0.99

 newspapers

0.96

 Newspapers

0.92

 Newspaper

0.88

newspaper

0.81

 Gleaner

0.75

 Zeitung

0.74

 Times

0.70

Newspaper

0.70

 periódico

0.68

Activations Density 0.103%

references to news organizations and publications

No Comments

No Known Activations