INDEX

Explanations

references to queries or searches related to information retrieval

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

 bezeichneter

-0.98

 تضيفلها

-0.73

XmlEnum

-0.70

SharedCtor

-0.64

parsedMessage

-0.63

');?>

-0.63

QMetaType

-0.62

 makl

-0.60

riguez

-0.59

verifyException

-0.59

POSITIVE LOGITS

Personendaten

0.55

WaitGroup

0.53

ManagedBean

0.49

 InputDecoration

0.48

Ligações

0.47

 StringVar

0.44

 censo

0.43

 eens

0.43

 chua

0.42

ołnier

0.42

Activations Density 1.632%

references to queries or searches related to information retrieval

No Comments

No Known Activations