INDEX

Explanations

numerical values and related statistical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 חיצוניים

-0.81

 désolés

-0.70

 Autorizaciones

-0.64

orsese

-0.63

ukone

-0.58

mybatisplus

-0.57

 Commencez

-0.55

hafen

-0.53

</thead>

-0.52

 useContext

-0.52

POSITIVE LOGITS

tonode

0.54

CreateMap

0.54

 consent

0.50

 Consent

0.48

anged

0.47

 Perio

0.47

writerow

0.46

SearchParams

0.45

kor

0.44

LabelTagHelper

0.44

Activations Density 0.196%

numerical values and related statistical terms

No Comments

No Known Activations