INDEX

Explanations

proper nouns, specifically names and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Monfieur

-0.76

 purpoſe

-0.72

 raiſ

-0.69

 onely

-0.67

 houſe

-0.65

Efq

-0.65

 femininas

-0.64

 marinho

-0.64

 leaſt

-0.63

 ſet

-0.63

POSITIVE LOGITS

ger

0.75

lat

0.70

Gre

0.68

ParallelGroup

0.67

ger

0.67

Utf

0.66

gre

0.66

Lat

0.66

utf

0.66

Yu

0.65

Activations Density 1.869%

proper nouns, specifically names and geographic locations

No Comments

No Known Activations