INDEX

Explanations

proper nouns related to locations and geographic entities

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

clerView

-0.47

-0.46

 initComponents

-0.46

tagHelperRunner

-0.46

 houſe

-0.44

ſelf

-0.43

 adquis

-0.42

 CreateTagHelper

-0.40

 rodea

-0.40

 sobě

-0.40

POSITIVE LOGITS

 Meksiku

0.53

 ब्रेकडाउन

0.49

CPtr

0.47

crollView

0.46

Vorlage

0.43

 <=",

0.43

 ویکی‌پدیا

0.42

EReference

0.41

 kasarigan

0.41

jsii

0.41

Activations Density 0.039%

proper nouns related to locations and geographic entities

No Comments

No Known Activations