INDEX

Explanations

the term "US" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Diſ

-0.76

 pleaſure

-0.68

 dAtA

-0.68

 Anſ

-0.66

 ་་

-0.66

 itſelf

-0.65

 leaſt

-0.65

 فريبيس

-0.64

 ―――――

-0.62

 Monfieur

-0.61

POSITIVE LOGITS

Us

1.03

US

0.87

Sol

0.78

us

0.75

Us

0.67

ząd

0.64

sol

0.60

 שוליים

0.60

memoized

0.59

SOL

0.58

Activations Density 0.116%

the term "US" in various contexts

No Comments

No Known Activations