INDEX

Explanations

questions about identity and agency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

Tradu

-0.67

esModule

-0.62

 Rasa

-0.58

 Highlands

-0.57

χα

-0.56

ματος

-0.56

 usus

-0.56

MST

-0.55

 exercise

-0.54

 Maiden

-0.54

POSITIVE LOGITS

 hvem

1.02

Who

1.01

Who

0.96

Кто

0.93

who

0.87

 Whom

0.87

who

0.87

Whoever

0.85

 Whoever

0.84

 Кто

0.84

Activations Density 0.072%

questions about identity and agency

No Comments

No Known Activations