INDEX

Explanations

light-hearted and entertaining reading experiences

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

+#+#

-0.65

 CreateTagHelper

-0.60

contentLoaded

-0.57

 بيها

-0.53

MathML

-0.51

帖最后由

-0.51

Looper

-0.50

Diwedd

-0.45

}}}}

-0.44

posals

-0.44

POSITIVE LOGITS

клопе

0.68

Démographie

0.66

 doInBackground

0.65

 enjoyable

0.62

 pleasant

0.60

 løpet

0.59

iotensin

0.56

sidemargin

0.56

FunctionFlags

0.56

 propOrder

0.56

Activations Density 0.005%

light-hearted and entertaining reading experiences

No Comments

No Known Activations