INDEX

Explanations

phrases related to personal preferences and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

expandindo

-0.79

ngdoc

-0.74

таратура

-0.63

MigrationBuilder

-0.63

THISDAY

-0.62

principalColumn

-0.61

DOCTYPE

-0.61

 الحره

-0.60

HasIndex

-0.60

########.

-0.59

POSITIVE LOGITS

webElementXpaths

0.52

sch

0.47

umy

0.45

ါ

0.45

介意

0.44

 just

0.44

تی

0.43

rungsseite

0.43

voit

0.41

Cha

0.41

Activations Density 0.260%

phrases related to personal preferences and experiences

No Comments

No Known Activations