INDEX

Explanations

code related to reading and processing JSON data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 AssemblyTitle

-0.94

Abitanti

-0.71

enderror

-0.70

Посилання

-0.66

PerformLayout

-0.65

 protoimpl

-0.65

contentLoaded

-0.63

 الحره

-0.63

 myſelf

-0.62

 Paglinawan

-0.61

POSITIVE LOGITS

 Iterator

0.61

Iterator

0.56

 inexhaustible

0.54

 cursor

0.53

 until

0.52

 while

0.49

enumi

0.49

 unending

0.48

 iterator

0.47

iterator

0.47

Activations Density 0.469%

code related to reading and processing JSON data

No Comments

No Known Activations