INDEX

Explanations

terms related to licenses and their governing language

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

="@+

-0.69

 getItemId

-0.68



-0.60

 pitié

-0.55

RemoveField

-0.55

herzog

-0.54

abestanden

-0.54

PageRoute

-0.54

 intptr

-0.54

dal

-0.53

POSITIVE LOGITS

 StringBuilder

0.64

DoubleQuotes

0.63

 StringBuffer

0.57

fromCharCode

0.57

 CODES

0.56

RenderAtEndOf

0.54

 الحره

0.54

sb

0.53

StandardCharsets

0.53

ymce

0.53

Activations Density 0.004%

terms related to licenses and their governing language

No Comments

No Known Activations