INDEX

Explanations

phrases and terms associated with medical conditions and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

TagMode

-0.86

IsContent

-0.79

InitVars

-0.72

клопе

-0.70

 оригіналу

-0.69

brainly

-0.67

tonode

-0.65

enumii

-0.65

 <<<<<<<<<<<<<<

-0.62

новништво

-0.62

POSITIVE LOGITS

 neko

0.46

but

0.46

 tuya

0.45

phylla

0.45

يمي

0.44

 Administrativna

0.44

 Dennoch

0.43

PerformLayout

0.43

('<

0.43

("<

0.42

Activations Density 0.511%

phrases and terms associated with medical conditions and their descriptions

No Comments

No Known Activations