INDEX

Explanations

locations or references to places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Personendaten

-0.86

 Algerian

-0.75

mphony

-0.66

 Estonian

-0.66

 Haitian

-0.65

 Kyrgyz

-0.65

 Guatem

-0.65

 Macedonian

-0.65

 Albanian

-0.64

awtextra

-0.64

POSITIVE LOGITS

 rural

0.80

 southern

0.75

 northern

0.68

 central

0.67

 sunny

0.65

 southeastern

0.65

 northeastern

0.62

 ancient

0.61

southern

0.60

rural

0.60

Activations Density 0.338%

locations or references to places

No Comments

No Known Activations