INDEX

Explanations

the word "or" in various contexts

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

Alternatives or possibilities

np_acts-logits-general · gemini-2.0-flash

alternative options

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.10

 Majefty

-1.08

 Shakspeare

-1.06

 ―――――

-1.05

 Jefus

-1.03

 Monfieur

-1.03

 Houſe

-1.02

 ་་

-0.98

 Anſ

-0.96

 uſed

-0.96

POSITIVE LOGITS

 even

1.18

 other

1.09

 otherwise

1.03

 else

1.00

any

0.99

 bahkan

0.94

 perhaps

0.93

otherwise

0.92

an

0.85

0.84

Activations Density 0.242%

the word "or" in various contexts

Alternatives or possibilities

alternative options

No Comments

No Known Activations