INDEX

Explanations

terms associated with health, medical conditions, and biological entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Photocase

-0.54

oa̍t

-0.49

 TextAppearance

-0.43

 تضيفلها

-0.41

sizeCache

-0.39

lesias

-0.36

cover

-0.35

expandindo

-0.35

 Pile

-0.35

 Mejor

-0.35

POSITIVE LOGITS

 Exacts

0.44

UserScript

0.43

期刊论文

0.43

enumi

0.42

enumii

0.40

 inalámbrica

0.40

 BoxDecoration

0.40

scriptcase

0.39

tdb

0.38

تقاوى

0.38

Activations Density 0.615%

terms associated with health, medical conditions, and biological entities

No Comments

No Known Activations