INDEX

Explanations

concepts and terminology related to immune responses and immune systems

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

carteles

-0.54

rsiniz

-0.47

ings

-0.45

 darb

-0.45

 consigo

-0.45

appartement

-0.45

deal

-0.45

rões

-0.43

 Lordships

-0.42

 escritório

-0.42

POSITIVE LOGITS

 Immune

1.05

Immune

1.01

 immune

0.98

immune

0.93

 immunity

0.69

 Immuno

0.69

 Immunity

0.67

 immuno

0.67

 autoimmune

0.66

 immun

0.64

Activations Density 0.013%

concepts and terminology related to immune responses and immune systems

No Comments

No Known Activations