INDEX

Explanations

references to various forms of "-ism" concepts, particularly in cultural, social, and economic contexts

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

⎩

-0.55

 Drury

-0.53

셨

-0.52

 Cleary

-0.51

Bef

-0.48

cros

-0.48

 Lipp

-0.46

 Cronin

-0.46

 Cline

-0.45

 stø

-0.45

POSITIVE LOGITS

ism

0.76

ArgsConstructor

0.75

queryInterface

0.73

IndentedString

0.68

textwidth

0.67

 tslint

0.64

Rid

0.64

 createState

0.63

 MenuView

0.63

enumii

0.63

Activations Density 2.205%

references to various forms of "-ism" concepts, particularly in cultural, social, and economic contexts

No Comments

No Known Activations