INDEX

Explanations

concepts related to definitions and formalities in theories or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 liné

-0.57

cektir

-0.53

 trách

-0.49

 belanja

-0.46

 quelcon

-0.45

endez

-0.45

χε

-0.45

rylic

-0.45

hum

-0.45

zzleHttp

-0.44

POSITIVE LOGITS

WithIOException

0.83

 invokingState

0.81

Билгалдахарш

0.78

 interrupted

0.67

 محفوظة

0.65

NameInMap

0.65

StoreMessageInfo

0.65

 postponed

0.64

VIAF

0.63

writeField

0.62

Activations Density 0.410%

concepts related to definitions and formalities in theories or systems

No Comments

No Known Activations