INDEX

Explanations

the word "an" 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 @ 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

bosity

-0.80

 saites

-0.78

NameInMap

-0.78

曖昧さ回避

-0.70

 sepen

-0.70

 Freeport

-0.70

pio

-0.70

fortable

-0.70

ılıyor

-0.69

 confor

-0.69

POSITIVE LOGITS

an

2.84

AN

1.87

an

1.31

An

1.04

anar

0.99

An

0.94

annya

0.91

anada

0.90

aná

0.89

anw

0.88

Activations Density 0.028%

the word "an" in various contexts

No Comments

No Known Activations