INDEX

Explanations

phrases related to medical or experimental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

GIVEREF

-0.61

MENAFN

-0.49

 envoyé

-0.47

 partagé

-0.46

 lenker

-0.45

hirts

-0.45

extr

-0.44

 sendMessage

-0.43

protoc

-0.43

руйте

-0.43

POSITIVE LOGITS

 cazul

0.87

SourceChecksum

0.81

 przypadku

0.74

KURZBESCHREIBUNG

0.70

 případ

0.67

RenderAtEndOf

0.66

 يتيمه

0.64

 Foire

0.63

 actionMode

0.63

hyrchwyd

0.61

Activations Density 1.225%

phrases related to medical or experimental contexts

No Comments

No Known Activations

phrases related to medical or experimental contexts

No Comments

No Known Activations