INDEX

Explanations

the use of the word "append" in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 nahilalakip

-0.99

 lenker

-0.96

 disambiguazione

-0.90

 Italijani

-0.88

 فريبيس

-0.87

WarningLevel

-0.87

 GoogleFonts

-0.86

OGND

-0.82

TagMode

-0.81

 contextLoads

-0.81

POSITIVE LOGITS

append

3.06

 append

2.63

 Append

2.39

Append

2.39

 APPEND

1.86

APPEND

1.81

 appended

1.64

 appendages

1.37

prepend

1.31

 appen

1.24

Activations Density 0.045%

the use of the word "append" in code snippets

No Comments

No Known Activations