INDEX

Explanations

indicators of false responses or inaccuracies in information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Wikimedijinoj

-0.58

DebuggerNonUser

-0.56

或

-0.51

 تعدى

-0.50

 definitely

-0.49

or

-0.48

 bete

-0.47

Якщо

-0.46

Chham

-0.45

Према

-0.45

POSITIVE LOGITS

BeginInit

0.84

 שוליים

0.64

]');

0.64

]='\

0.64

>';

0.62

](#

0.62

 فريبيس

0.62

новништво

0.61

 discusses

0.61

ISupport

0.60

Activations Density 0.058%

indicators of false responses or inaccuracies in information

No Comments

No Known Activations