INDEX

Explanations

phrases expressing possibilities or hypothetical scenarios

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

endphp

-0.60

 AspNetCore

-0.54

 gelernt

-0.52

__":

-0.52

 useParams

-0.51

__":

-0.51

webElementXpaths

-0.50

Hauptartikel

-0.49

 kultury

-0.47

ReusableCell

-0.46

POSITIVE LOGITS

 could

1.17

could

1.13

 Could

1.08

 COULD

1.08

Could

1.06

 potentially

1.01

 conceivably

0.99

potentially

0.98

 könnte

0.93

 possibly

0.87

Activations Density 0.184%

phrases expressing possibilities or hypothetical scenarios

No Comments

No Known Activations