INDEX

Explanations

expressions related to hypocrisy or inconsistencies in statements or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Parcelize

-0.69

 Мексичка

-0.66

Carriera

-0.62

InstrumentedTest

-0.58

 Signalez

-0.57

NOPQRST

-0.56

 useAppContext

-0.56

—

-0.54

IUrlHelper

-0.54

 Савезне

-0.53

POSITIVE LOGITS

IVEREF

0.65

herty

0.56

 Verbre

0.54

ercises

0.49

 adjournment

0.48

กัน

0.47

leistungs

0.47

 Arag

0.46

 overload

0.46

DropTable

0.44

Activations Density 0.397%

expressions related to hypocrisy or inconsistencies in statements or behaviors

No Comments

No Known Activations