INDEX

Explanations

terms related to programming and coding constructs

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

ंदीखरीदारी

-0.53

 pure

-0.51

γη

-0.50

 fire

-0.49

 跳转至

-0.48

appendTo

-0.47

 assist

-0.47

 star

-0.46

 simplifié

-0.46

ћи

-0.46

POSITIVE LOGITS

able

0.73

 Roskov

0.64

GroupLayout

0.62

ability

0.60

Становништво

0.59

 Superhost

0.58

UnusedPrivate

0.57

bootstrapcdn

0.54

 Приступљено

0.54

 moeite

0.53

Activations Density 2.239%

terms related to programming and coding constructs

No Comments

No Known Activations