INDEX

Explanations

assertions in code testing, particularly related to object properties and their attributes

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

Followed by `toBe` or `EqualTo`

np_acts-logits-general · gemini-2.0-flash

testing assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 EconPapers

-0.86

DockStyle

-0.78

fjspx

-0.76

setVerticalGroup

-0.74

enumi

-0.74

StructEnd

-0.73

Personendaten

-0.72

 otomatig

-0.71

CodeAttribute

-0.71

prnewswire

-0.70

POSITIVE LOGITS

 equal

0.47

 paille

0.46

 equality

0.44

NOT

0.44

not

0.44

mení

0.44

 breech

0.43

 Mannes

0.42

 have

0.41

not

0.41

Activations Density 0.095%

assertions in code testing, particularly related to object properties and their attributes

Followed by `toBe` or `EqualTo`

testing assertions

No Comments

No Known Activations