INDEX

Explanations

instances of the word "new."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 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

 őket

-0.63

 sanitarias

-0.62

 Assisi

-0.61

 umano

-0.60

 umane

-0.60

 antaranya

-0.59

 cardiaque

-0.59

 énergétique

-0.57

 laborales

-0.56

 ILogger

-0.56

POSITIVE LOGITS

new

3.59

new

2.83

 nieuwe

2.48

 neue

2.35

 nuevos

2.34

 nueva

2.33

新的

2.33

 nuevas

2.33

 neuen

2.27

 nuevo

2.15

Activations Density 0.099%

instances of the word "new."

No Comments

No Known Activations