INDEX

Explanations

instances of the word "display" and related terms indicating visualization or presentation

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

 kaynağından

-0.69

ContentAsync

-0.60

 généraux

-0.60

 conseille

-0.59

ftagPool

-0.58

 aluguel

-0.58

(!__

-0.58

 člá

-0.57

fcntl

-0.57

netty

-0.56

POSITIVE LOGITS

 displaying

2.85

 showing

2.79

 displays

2.75

 display

2.70

 Showing

2.58

 show

2.54

 Show

2.46

showing

2.41

 demonstrating

2.38

Show

2.38

Activations Density 0.150%

instances of the word "display" and related terms indicating visualization or presentation

No Comments

No Known Activations