INDEX

Explanations

occurrences of comments in code

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

waiting for completion

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

Spoljašnje

-0.71

AdapterFactory

-0.68

thâu

-0.55

 دیکھیے

-0.54

DataContract

-0.52

ệu

-0.52

OwnProperty

-0.50

 useAuth

-0.50

nessed

-0.49

 باخ

-0.49

POSITIVE LOGITS

#+#

0.66

帖最后由

0.64

:✨

0.62

 Both

0.57

The

0.57

pośred

0.57

 <<<<<<<<<<<<<<

0.56

 végétale

0.54

OrBuilder

0.54

お願いします

0.54

Activations Density 0.027%

occurrences of comments in code

waiting for completion

No Comments

No Known Activations