INDEX

Explanations

elements related to reports or announcements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 României

-0.54

 SafeMath

-0.52

KURZBESCHREIBUNG

-0.52

tvguidetime

-0.51

uttore

-0.50

 okuyayım

-0.49

 Combien

-0.47

 ombro

-0.46

meist

-0.45

ngdoc

-0.45

POSITIVE LOGITS

SequentialGroup

0.81

SourceChecksum

0.80

ագրություններ

0.79

bootstrapcdn

0.72

vician

0.60

 pinulongan

0.59

ynia

0.59

 namens

0.59

jsonwebtoken

0.59

fällig

0.59

Activations Density 1.235%

elements related to reports or announcements in various contexts

No Comments

No Known Activations