INDEX

Explanations

relationships and comparisons in scientific data regarding various health-related measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

AxisAlignment

-0.60

 beginnetje

-0.60

 Administrativna

-0.54

SharedDtor

-0.53

QtCore

-0.51

 sbag

-0.46

istoitu

-0.45

 doInBackground

-0.44

 simplifié

-0.43

 perfons

-0.43

POSITIVE LOGITS

 observed

2.21

observed

1.86

 detected

1.70

 reported

1.65

 Observed

1.64

 recorded

1.55

 noticed

1.54

 found

1.53

 discovered

1.51

Observed

1.46

Activations Density 1.430%

relationships and comparisons in scientific data regarding various health-related measurements

No Comments

No Known Activations