INDEX

Explanations

phrases expressing doubt and uncertainty regarding claims or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 otomatig

-0.69

AndroidJUnit

-0.66

webElementXpaths

-0.55

олові

-0.53

AnchorTagHelper

-0.52

 "..\..\..\

-0.52

 Sante

-0.52

 iNdEx

-0.50

SOUNDBITE

-0.50

 AssemblyCulture

-0.49

POSITIVE LOGITS

 doubt

2.71

 doubts

2.48

 doubted

2.21

doubt

2.19

 Doubt

2.13

 doubting

2.00

Doubt

2.00

 doubtful

1.97

 doute

1.79

 сом

1.75

Activations Density 0.441%

phrases expressing doubt and uncertainty regarding claims or evidence

No Comments

No Known Activations