INDEX

Explanations

words related to medical and scientific processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

âtre

-0.53

تقاوى

-0.52

dominant

-0.50

Erreferentziak

-0.47

ամ

-0.47

-0.46

 someone

-0.46

Personendaten

-0.45

шна

-0.45

OneToMany

-0.45

POSITIVE LOGITS

istoitu

1.13

########.

0.93

 iNdEx

0.74

 Translated

0.71

 mined

0.70

roidered

0.69

])));

0.69

 Analyzed

0.68

hopped

0.67

 Processed

0.67

Activations Density 0.578%

words related to medical and scientific processes

No Comments

No Known Activations