INDEX

Explanations

phrases indicating capability or ability to interfere and affect outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Становништво

-0.64

 وتسجيلات

-0.59

Autoritní

-0.58

ViewFeatures

-0.58

 chi̍t

-0.56

 سكانية

-0.55

fortawesome

-0.55

 isInitialized

-0.55

 termica

-0.55

 montagna

-0.53

POSITIVE LOGITS

AndEndTag

0.64

cu

0.54

SpringBootTest

0.51

AddHtmlAttribute

0.50

 DBNull

0.50

kheim

0.49

Cu

0.48

 Utile

0.48

 Rango

0.47

 Gage

0.47

Activations Density 0.889%

phrases indicating capability or ability to interfere and affect outcomes

No Comments

No Known Activations