INDEX

Explanations

references to emotional suffering and psychological states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

findpost

-0.77

 nahilalakip

-0.70

mazaki

-0.66

🎰

-0.65

 متعلقه

-0.64

íncia

-0.64

føl

-0.64

alchemy

-0.63

ścic

-0.62

例句

-0.60

POSITIVE LOGITS

 AssemblyCulture

0.50

StoryboardSegue

0.48

gtest

0.46

GeneratedValue

0.44

 autorytatywna

0.42

envolvimento

0.40

(_.

0.40

 Процитовано

0.39

newswire

0.39

forRoot

0.38

Activations Density 0.132%

references to emotional suffering and psychological states

No Comments

No Known Activations