INDEX

Explanations

terms related to slavery and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 teleport

-0.57

 ſta

-0.56

ronyms

-0.56

󠁢

-0.55

lapia

-0.54

BibitemShut

-0.54

 ThemeData

-0.54

 shipbuilding

-0.52

 AssemblyCompany

-0.52

ſelf

-0.52

POSITIVE LOGITS

zo

0.81

して

0.62

 slave

0.56

Sur

0.54

ZO

0.54

ics

0.49

tics

0.49

richTextPanel

0.48

ICS

0.47

 candle

0.46

Activations Density 0.346%

terms related to slavery and related concepts

No Comments

No Known Activations