INDEX

Explanations

programming-related assertions and object expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Hentet

-0.64

ValueStyle

-0.61

setVerticalGroup

-0.60

 >=",

-0.57

AddTagHelper

-0.57

 autorytatywna

-0.56

 CreateTagHelper

-0.56

ConstraintMaker

-0.56

principalTable

-0.55

loài

-0.53

POSITIVE LOGITS

таратура

0.58

DIPSETTING

0.54

̀ng

0.53

 heureuse

0.53

版

0.53

AndView

0.52

 Soud

0.51

 whoſe

0.51

PreferredItem

0.51

 skjø

0.50

Activations Density 0.669%

programming-related assertions and object expectations

No Comments

No Known Activations