INDEX

Explanations

terms related to specific software functionalities and features

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.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

 незавершена

-1.02

 CreateTagHelper

-0.84

Fordítás

-0.71

">—

-0.69

LookAnd

-0.69

 dAtA

-0.69

WithIOException

-0.68

verwijspagina

-0.68

 WaitForSeconds

-0.66

awtextra

-0.65

POSITIVE LOGITS

("")]

0.60

 plagioclase

0.51

 Centuries

0.50

veille

0.48

ATTLE

0.47

ution

0.46

zczy

0.45

 Antik

0.45

 proceeds

0.44

 conclusão

0.44

Activations Density 0.048%

terms related to specific software functionalities and features

No Comments

No Known Activations