INDEX

Explanations

references to geographical locations and islands

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Mugh

-0.67

 bezeichneter

-0.66

 Clovis

-0.61

ględ

-0.60

潢

-0.58

はじめに

-0.58

 kasarigan

-0.56

 Ravenna

-0.56

 Rembrandt

-0.56

getLayout

-0.56

POSITIVE LOGITS

 island

1.46

 Island

1.41

 Islands

1.31

island

1.28

 islands

1.25

 ISLAND

1.24

Island

1.20

 islanders

1.14

Islands

1.11

 ISLANDS

1.04

Activations Density 0.171%

references to geographical locations and islands

No Comments

No Known Activations