INDEX

Explanations

programming constructs related to iterating through collections or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zerű

-0.59

gatan

-0.49

neurial

-0.48

 Coutinho

-0.48

apatalk

-0.48

GGI

-0.46

bootstrapcdn

-0.45

 bittersweet

-0.45

 điệu

-0.44

ulfon

-0.44

POSITIVE LOGITS

 &___

0.84

 autorytatywna

0.83

tagHelperRunner

0.81

 nahilalakip

0.72

Autoritní

0.66

forChild

0.65

 InputDecoration

0.63

netbeans

0.63

 relâche

0.60

 StringTokenizer

0.59

Activations Density 0.094%

programming constructs related to iterating through collections or data structures

No Comments

No Known Activations