INDEX

Explanations

coding terms related to defining and utilizing functions or methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

发表于

-0.92

UserScript

-0.87

 localObject

-0.63

awtextra

-0.63

 contextLoads

-0.63

 تضيفلها

-0.62

/>\

-0.62

OrNil

-0.62

endregion

-0.60

\{\\

-0.60

POSITIVE LOGITS

 preocupes

0.49

 AssemblyCulture

0.49

 publiques

0.48

 ventaja

0.47

ellschaft

0.46

 zulassen

0.46

 keuntungan

0.45

 appartiennent

0.45

 chaude

0.45

 tradisional

0.44

Activations Density 0.638%

coding terms related to defining and utilizing functions or methods

No Comments

No Known Activations